arXiv subjects

Zhengqiang Zhang

Publications and source records attributed to Zhengqiang Zhang.

At least 19 recordsLinked to original sources

arXiv2026

LDM-is-AE: Latent Diffusion Model is an Auto-Encoder for End-to-End Image Generation

Latent Diffusion Models (LDMs) typically adopt a two-stage pipeline: an auto-encoder (AE) is first pre-trained to define a latent space, then a diffusion model is trained to perform denoising within it. Such a two-stage design introduces a representation mismatch, as the latent space is optimized for reconstruction rather than adapting the denoising dynamics. We reveal that the LDM itself is an AE, and consequently present LDM-is-AE, an end-to-end one-stage LDM training framework that eliminates the need for a separately trained tokenizer. Our key observation is that the LDM backbone actually performs a latent-to-feature-to-latent transformation at each denoising step, which can be interpreted as an internal decoding--encoding process. Leveraging this structure, we split the DiT backbone into two reciprocal components, DiT-E (i.e., DiT Encoding) and DiT-D (i.e., DiT Decoding), and impose image-space supervision on the intermediate features across all timesteps. Our model encourages the internal representation to align with the image domain throughout denoising, thereby establishing an explicit latent-to-image-to-latent path. At the zero-noise timestep, our model further performs an image-to-latent-to-image mapping, corresponding to an auto-encoding process. As a result, LDM-is-AE jointly learns latent representations and denoising dynamics in an end-to-end manner, yielding a diffusion-native latent space tailored to the generation process. Experiments demonstrate that LDM-is-AE exhibits highly competitive generation performance, achieving an FID of 1.80 and 1.90 on 256x256 and 512x512 class-conditional image generation, respectively.

cs.CV↗

arXiv2026

Reduced Cartesian Kinetostatics for Tendon-Driven Continuum Robots: Residual-Stabilized Full-Shape Propagation

Many planning and control tasks for tendon-driven continuum robots (TDCRs) require the complete Cartesian backbone geometry. We present a reduced Cartesian framework for planar, axially compressible TDCRs that propagates equilibrium configurations along prescribed tendon-force and tendon-displacement trajectories. The backbone is represented by two global position fields. Following exact variation, a Taylor-Galerkin reduction condenses prescribed spatial properties and distributed loads into offline moment vectors, yielding analytic reduced residuals and Jacobians without online spatial quadrature or numerical differentiation. Analytical differentiation and residual correction yield first-order rate systems requiring one fixed-dimensional linear solve per rate evaluation after initial equilibrium alignment on a regular branch. Across four simulated cases covering variable tendon routing, nonuniform geometry, axial compression, and their combined effects, the propagated Cartesian shapes and distributed strains closely match pointwise geometrically variable-strain (GVS) equilibrium solutions. Residual correction suppresses propagation drift across the tested step sizes while adding only about 0.98% to the mean update time of uncorrected Euler. The proposed method requires 0.508 ms per update on average, approximately 11 times faster than pointwise GVS solves. Displacement-driven experiments yield a maximum normalized mean backbone position error of 1.02% and a maximum end-effector position error of 0.28%. These results support efficient and accurate Cartesian full-shape prediction along prescribed actuation paths.

cs.RO↗

arXiv2026

PixRestore: Unified Image Restoration via Pixel Diffusion Transformer

Unified image restoration (UIR) aims to recover high-quality (HQ) content from low-quality (LQ) images with different degradations using a single model. Most recent methods adapt large pretrained text-to-image (T2I) latent diffusion models for their strong capacity and generative priors. However, the variational autoencoder (VAE) in latent T2I models may discard restoration-sensitive details, while the open-ended synthesis prior can introduce content-inconsistent artifacts. We present PixRestore, a VAE-free pixel-space Diffusion Transformer (DiT) for UIR, where the diffusion backbone is trained entirely from scratch, without relying on T2I pretraining. PixRestore performs flow matching directly on patchified pixels, preserving fine-grained details while keeping the token sequence tractable. To adapt to different degradations, PixRestore learns to predict the reliability of layer features using LQ--HQ DINO feature similarity. Features from more reliable layers are fused as dense conditioning, while less reliable layers receive stronger HQ-feature supervision to encourage degradation removal. We train PixRestore on a large-scale corpus of diverse scenes and degradations, and further finetune it into a one-step generator using DINO-based adversarial objectives for efficient inference. Experiments on public benchmarks and real-world test sets show that, with only about 50M parameters and single-step inference, PixRestore achieves the best overall fidelity, perceptual quality, and robustness to degradations among competing UIR models while being far more efficient. Larger PixRestore variants can further boost performance, demonstrating the scalability of our pixel-space design. Code and the curated benchmark can be found at https://github.com/csslc/PixRestore.

cs.CV↗

arXiv2026

Self-transcendence: Is External Feature Guidance Indispensable for Accelerating Diffusion Transformer Training?

Recent works such as REPA have shown that guiding diffusion models with external semantic features (e.g., DINO) can significantly accelerate the training of diffusion transformers (DiTs). However, the use of pretrained external features as guidance signals introduces additional dependencies. We argue that DiTs actually have the power to guide the training of themselves, and propose SelfTranscendence, an effective method that achieves fast convergence using internal feature supervision only. The desired internal guidance features should meet two requirements: structurally clean to help shallow blocks separate noise from signal, and semantically discriminative to help shallow layers learn effective representations. With this consideration, we first align the DiT features with the clean VAE latent features, a native component of latent diffusion, for a short training phase (e.g., 40 epochs) to improve their structural representations, then apply the classifier-free guidance to the intermediate features, enhancing their discriminative capability and semantic expressiveness. These enriched internal features, learned entirely within the model, are used as supervision signals to guide a new DiT training from scratch. Compared to existing self-contained methods, our approach achieves a significant performance boost. It can even surpass REPA, which uses the external DINO features as guidance, in both generation quality and convergence speed for both class-to-image and text-to-image generation tasks. The source code of our method can be found at https://github.com/csslc/Self-Transcendence.

cs.CV↗

arXiv2026

Memorize When Needed: Decoupled Memory Control for Spatially Consistent Long-Horizon Video Generation

Spatially consistent long-horizon video generation aims to maintain temporal and spatial consistency along predefined camera trajectories. Existing methods mostly entangle memory modeling with video generation, leading to inconsistent content during scene revisits and diminished generative capacity when exploring novel regions, even trained on extensive annotated data. To address these limitations, we propose a decoupled framework that separates memory conditioning from generation. Our approach significantly reduces training costs while simultaneously enhancing spatial consistency and preserving the generative capacity for novel scene exploration. Specifically, we employ a lightweight, independent memory branch to learn precise spatial consistency from historical observation. We first introduce a hybrid memory representation to capture complementary temporal and spatial cues from generated frames, then leverage a per-frame cross-attention mechanism to ensure each frame is conditioned exclusively on the most spatially relevant historical information, which is injected into the generative model to ensure spatial consistency. When generating new scenes, a camera-aware gating mechanism is proposed to mediate the interaction between memory and generation modules, enabling memory conditioning only when meaningful historical references exist. Compared with the existing method, our method is highly data-efficient, yet the experiments demonstrate that our approach achieves state-of-the-art performance in terms of both visual quality and spatial consistency.

cs.CV↗

arXiv2026

VOSR: A Vision-Only Generative Model for Image Super-Resolution

Most of the recent generative image super-resolution (SR) methods rely on adapting large text-to-image (T2I) diffusion models pretrained on web-scale text-image data. While effective, this paradigm starts from a generic T2I generator, despite that SR is fundamentally a low-resolution (LR) input-conditioned image restoration task. In this work, we investigate whether an SR model trained purely on visual data can rival T2I-based ones. To this end, we propose VOSR, a Vision-Only generative framework for SR. We first extract semantically rich and spatially grounded features from the LR input using a pretrained vision encoder as visual semantic guidance. We then revisit classifier-free guidance for training generative models and show that the standard unconditional branch is ill-suited to restoration models trained from scratch. We therefore replace it with a restoration-oriented guidance strategy that preserves weak LR anchors. Built upon these designs, we first train a multi-step VOSR model from scratch and then distill it into a one-step model for efficient inference. VOSR requires less than one-tenth of the training cost of representative T2I-based SR methods, yet in both multi-step and one-step settings, it achieves competitive or even better perceptual quality and efficiency, while producing more faithful structures with fewer hallucinations on both synthetic and real-world benchmarks. Our results, for the first time, show that high-quality generative SR can be achieved without multimodal pretraining. The code and models can be found at https://github.com/cswry/VOSR.

cs.CV↗

arXiv2026

GDPO-SR: Group Direct Preference Optimization for One-Step Generative Image Super-Resolution

Recently, reinforcement learning (RL) has been employed for improving generative image super-resolution (ISR) performance. However, the current efforts are focused on multi-step generative ISR, while one-step generative ISR remains underexplored due to its limited stochasticity. In addition, RL methods such as Direct Preference Optimization (DPO) require the generation of positive and negative sample pairs offline, leading to a limited number of samples, while Group Relative Policy Optimization (GRPO) only calculates the likelihood of the entire image, ignoring local details that are crucial for ISR. In this paper, we propose Group Direct Preference Optimization (GDPO), a novel approach to integrate RL into one-step generative ISR model training. First, we introduce a noise-aware one-step diffusion model that can generate diverse ISR outputs. To prevent performance degradation caused by noise injection, we introduce an unequal-timestep strategy to decouple the timestep of noise addition from that of diffusion. We then present the GDPO strategy, which integrates the principle of GRPO into DPO, to calculate the group-relative advantage of each online generated sample for model optimization. Meanwhile, an attribute-aware reward function is designed to dynamically evaluate the score of each sample based on its statistics of smooth and texture areas. Experiments demonstrate the effectiveness of GDPO in enhancing the performance of one-step generative ISR models. Code: https://github.com/Joyies/GDPO.

cs.CV↗

arXiv2026

BinaryAttention: One-Bit QK-Attention for Vision and Diffusion Transformers

Transformers have achieved widespread and remarkable success, while the computational complexity of their attention modules remains a major bottleneck for vision tasks. Existing methods mainly employ 8-bit or 4-bit quantization to balance efficiency and accuracy. In this paper, with theoretical justification, we indicate that binarization of attention preserves the essential similarity relationships, and propose BinaryAttention, an effective method for fast and accurate 1-bit qk-attention. Specifically, we retain only the sign of queries and keys in computing the attention, and replace the floating dot products with bit-wise operations, significantly reducing the computational cost. We mitigate the inherent information loss under 1-bit quantization by incorporating a learnable bias, and enable end-to-end acceleration. To maintain the accuracy of attention, we adopt quantization-aware training and self-distillation techniques, mitigating quantization errors while ensuring sign-aligned similarity. BinaryAttention is more than 2x faster than FlashAttention2 on A100 GPUs. Extensive experiments on vision transformer and diffusion transformer benchmarks demonstrate that BinaryAttention matches or even exceeds full-precision attention, validating its effectiveness. Our work provides a highly efficient and effective alternative to full-precision attention, pushing the frontier of low-bit vision and diffusion transformers. The codes and models can be found at https://github.com/EdwardChasel/BinaryAttention.

cs.CV↗

arXiv2025

One-Step Diffusion for Detail-Rich and Temporally Consistent Video Super-Resolution

It is a challenging problem to reproduce rich spatial details while maintaining temporal consistency in real-world video super-resolution (Real-VSR), especially when we leverage pre-trained generative models such as stable diffusion (SD) for realistic details synthesis. Existing SD-based Real-VSR methods often compromise spatial details for temporal coherence, resulting in suboptimal visual quality. We argue that the key lies in how to effectively extract the degradation-robust temporal consistency priors from the low-quality (LQ) input video and enhance the video details while maintaining the extracted consistency priors. To achieve this, we propose a Dual LoRA Learning (DLoRAL) paradigm to train an effective SD-based one-step diffusion model, achieving realistic frame details and temporal consistency simultaneously. Specifically, we introduce a Cross-Frame Retrieval (CFR) module to aggregate complementary information across frames, and train a Consistency-LoRA (C-LoRA) to learn robust temporal representations from degraded inputs. After consistency learning, we fix the CFR and C-LoRA modules and train a Detail-LoRA (D-LoRA) to enhance spatial details while aligning with the temporal space defined by C-LoRA to keep temporal coherence. The two phases alternate iteratively for optimization, collaboratively delivering consistent and detail-rich outputs. During inference, the two LoRA branches are merged into the SD model, allowing efficient and high-quality video restoration in a single diffusion step. Experiments show that DLoRAL achieves strong performance in both accuracy and speed. Code and models are available at https://github.com/yjsunnn/DLoRAL.

cs.CV↗

arXiv2025

DP$^2$O-SR: Direct Perceptual Preference Optimization for Real-World Image Super-Resolution

Benefiting from pre-trained text-to-image (T2I) diffusion models, real-world image super-resolution (Real-ISR) methods can synthesize rich and realistic details. However, due to the inherent stochasticity of T2I models, different noise inputs often lead to outputs with varying perceptual quality. Although this randomness is sometimes seen as a limitation, it also introduces a wider perceptual quality range, which can be exploited to improve Real-ISR performance. To this end, we introduce Direct Perceptual Preference Optimization for Real-ISR (DP$^2$O-SR), a framework that aligns generative models with perceptual preferences without requiring costly human annotations. We construct a hybrid reward signal by combining full-reference and no-reference image quality assessment (IQA) models trained on large-scale human preference datasets. This reward encourages both structural fidelity and natural appearance. To better utilize perceptual diversity, we move beyond the standard best-vs-worst selection and construct multiple preference pairs from outputs of the same model. Our analysis reveals that the optimal selection ratio depends on model capacity: smaller models benefit from broader coverage, while larger models respond better to stronger contrast in supervision. Furthermore, we propose hierarchical preference optimization, which adaptively weights training pairs based on intra-group reward gaps and inter-group diversity, enabling more efficient and stable learning. Extensive experiments across both diffusion- and flow-based T2I backbones demonstrate that DP$^2$O-SR significantly improves perceptual quality and generalizes well to real-world benchmarks.

cs.CV↗

arXiv2025

GPSToken: Gaussian Parameterized Spatially-adaptive Tokenization for Image Representation and Generation

Effective and efficient tokenization plays an important role in image representation and generation. Conventional methods, constrained by uniform 2D/1D grid tokenization, are inflexible to represent regions with varying shapes and textures and at different locations, limiting their efficacy of feature representation. In this work, we propose $\textbf{GPSToken}$, a novel $\textbf{G}$aussian $\textbf{P}$arameterized $\textbf{S}$patially-adaptive $\textbf{Token}$ization framework, to achieve non-uniform image tokenization by leveraging parametric 2D Gaussians to dynamically model the shape, position, and textures of different image regions. We first employ an entropy-driven algorithm to partition the image into texture-homogeneous regions of variable sizes. Then, we parameterize each region as a 2D Gaussian (mean for position, covariance for shape) coupled with texture features. A specialized transformer is trained to optimize the Gaussian parameters, enabling continuous adaptation of position/shape and content-aware feature extraction. During decoding, Gaussian parameterized tokens are reconstructed into 2D feature maps through a differentiable splatting-based renderer, bridging our adaptive tokenization with standard decoders for end-to-end training. GPSToken disentangles spatial layout (Gaussian parameters) from texture features to enable efficient two-stage generation: structural layout synthesis using lightweight networks, followed by structure-conditioned texture generation. Experiments demonstrate the state-of-the-art performance of GPSToken, which achieves rFID and FID scores of 0.65 and 1.50 on image reconstruction and generation tasks using 128 tokens, respectively. Codes and models of GPSToken can be found at $\href{https://github.com/xtudbxk/GPSToken}{https://github.com/xtudbxk/GPSToken}$.

cs.CV↗

arXiv2025

Generalized and Efficient 2D Gaussian Splatting for Arbitrary-scale Super-Resolution

Implicit Neural Representations (INR) have been successfully employed for Arbitrary-scale Super-Resolution (ASR). However, INR-based models need to query the multi-layer perceptron module numerous times and render a pixel in each query, resulting in insufficient representation capability and low computational efficiency. Recently, Gaussian Splatting (GS) has shown its advantages over INR in both visual quality and rendering speed in 3D tasks, which motivates us to explore whether GS can be employed for the ASR task. However, directly applying GS to ASR is exceptionally challenging because the original GS is an optimization-based method through overfitting each single scene, while in ASR we aim to learn a single model that can generalize to different images and scaling factors. We overcome these challenges by developing two novel techniques. Firstly, to generalize GS for ASR, we elaborately design an architecture to predict the corresponding image-conditioned Gaussians of the input low-resolution image in a feed-forward manner. Each Gaussian can fit the shape and direction of an area of complex textures, showing powerful representation capability. Secondly, we implement an efficient differentiable 2D GPU/CUDA-based scale-aware rasterization to render super-resolved images by sampling discrete RGB values from the predicted continuous Gaussians. Via end-to-end training, our optimized network, namely GSASR, can perform ASR for any image and unseen scaling factors. Extensive experiments validate the effectiveness of our proposed method. The code and models are available at https://github.com/ChrisDud0257/GSASR.

eess.IV↗

arXiv2025

NTIRE 2025 the 2nd Restore Any Image Model (RAIM) in the Wild Challenge

In this paper, we present a comprehensive overview of the NTIRE 2025 challenge on the 2nd Restore Any Image Model (RAIM) in the Wild. This challenge established a new benchmark for real-world image restoration, featuring diverse scenarios with and without reference ground truth. Participants were tasked with restoring real-captured images suffering from complex and unknown degradations, where both perceptual quality and fidelity were critically evaluated. The challenge comprised two tracks: (1) the low-light joint denoising and demosaicing (JDD) task, and (2) the image detail enhancement/generation task. Each track included two sub-tasks. The first sub-task involved paired data with available ground truth, enabling quantitative evaluation. The second sub-task dealt with real-world yet unpaired images, emphasizing restoration efficiency and subjective quality assessed through a comprehensive user study. In total, the challenge attracted nearly 300 registrations, with 51 teams submitting more than 600 results. The top-performing methods advanced the state of the art in image restoration and received unanimous recognition from all 20+ expert judges. The datasets used in Track 1 and Track 2 are available at https://drive.google.com/drive/folders/1Mgqve-yNcE26IIieI8lMIf-25VvZRs_J and https://drive.google.com/drive/folders/1UB7nnzLwqDZOwDmD9aT8J0KVg2ag4Qae, respectively. The official challenge pages for Track 1 and Track 2 can be found at https://codalab.lisn.upsaclay.fr/competitions/21334#learn_the_details and https://codalab.lisn.upsaclay.fr/competitions/21623#learn_the_details.

eess.IV↗

arXiv2025

FreCaS: Efficient Higher-Resolution Image Generation via Frequency-aware Cascaded Sampling

While image generation with diffusion models has achieved a great success, generating images of higher resolution than the training size remains a challenging task due to the high computational cost. Current methods typically perform the entire sampling process at full resolution and process all frequency components simultaneously, contradicting with the inherent coarse-to-fine nature of latent diffusion models and wasting computations on processing premature high-frequency details at early diffusion stages. To address this issue, we introduce an efficient $\textbf{Fre}$quency-aware $\textbf{Ca}$scaded $\textbf{S}$ampling framework, $\textbf{FreCaS}$ in short, for higher-resolution image generation. FreCaS decomposes the sampling process into cascaded stages with gradually increased resolutions, progressively expanding frequency bands and refining the corresponding details. We propose an innovative frequency-aware classifier-free guidance (FA-CFG) strategy to assign different guidance strengths for different frequency components, directing the diffusion model to add new details in the expanded frequency domain of each stage. Additionally, we fuse the cross-attention maps of previous and current stages to avoid synthesizing unfaithful layouts. Experiments demonstrate that FreCaS significantly outperforms state-of-the-art methods in image quality and generation speed. In particular, FreCaS is about 2.86$\times$ and 6.07$\times$ faster than ScaleCrafter and DemoFusion in generating a 2048$\times$2048 image using a pre-trained SDXL model and achieves an FID$_b$ improvement of 11.6 and 3.7, respectively. FreCaS can be easily extended to more complex models such as SD3. The source code of FreCaS can be found at https://github.com/xtudbxk/FreCaS.

cs.CV↗

arXiv2025

Spatial-Mamba: Effective Visual State Space Models via Structure-aware State Fusion

Selective state space models (SSMs), such as Mamba, highly excel at capturing long-range dependencies in 1D sequential data, while their applications to 2D vision tasks still face challenges. Current visual SSMs often convert images into 1D sequences and employ various scanning patterns to incorporate local spatial dependencies. However, these methods are limited in effectively capturing the complex image spatial structures and the increased computational cost caused by the lengthened scanning paths. To address these limitations, we propose Spatial-Mamba, a novel approach that establishes neighborhood connectivity directly in the state space. Instead of relying solely on sequential state transitions, we introduce a structure-aware state fusion equation, which leverages dilated convolutions to capture image spatial structural dependencies, significantly enhancing the flow of visual contextual information. Spatial-Mamba proceeds in three stages: initial state computation in a unidirectional scan, spatial context acquisition through structure-aware state fusion, and final state computation using the observation equation. Our theoretical analysis shows that Spatial-Mamba unifies the original Mamba and linear attention under the same matrix multiplication framework, providing a deeper understanding of our method. Experimental results demonstrate that Spatial-Mamba, even with a single scan, attains or surpasses the state-of-the-art SSM-based models in image classification, detection and segmentation. Source codes and trained models can be found at https://github.com/EdwardChasel/Spatial-Mamba.

cs.CV↗

arXiv2024

Improving the Stability and Efficiency of Diffusion Models for Content Consistent Super-Resolution

The generative priors of pre-trained latent diffusion models (DMs) have demonstrated great potential to enhance the visual quality of image super-resolution (SR) results. However, the noise sampling process in DMs introduces randomness in the SR outputs, and the generated contents can differ a lot with different noise samples. The multi-step diffusion process can be accelerated by distilling methods, but the generative capacity is difficult to control. To address these issues, we analyze the respective advantages of DMs and generative adversarial networks (GANs) and propose to partition the generative SR process into two stages, where the DM is employed for reconstructing image structures and the GAN is employed for improving fine-grained details. Specifically, we propose a non-uniform timestep sampling strategy in the first stage. A single timestep sampling is first applied to extract the coarse information from the input image, then a few reverse steps are used to reconstruct the main structures. In the second stage, we finetune the decoder of the pre-trained variational auto-encoder by adversarial GAN training for deterministic detail enhancement. Once trained, our proposed method, namely content consistent super-resolution (CCSR),allows flexible use of different diffusion steps in the inference stage without re-training. Extensive experiments show that with 2 or even 1 diffusion step, CCSR can significantly improve the content consistency of SR outputs while keeping high perceptual quality. Codes and models can be found at \href{https://github.com/csslc/CCSR}{https://github.com/csslc/CCSR}.

eess.IV↗

arXiv2024

SSL: A Self-similarity Loss for Improving Generative Image Super-resolution

Generative adversarial networks (GAN) and generative diffusion models (DM) have been widely used in real-world image super-resolution (Real-ISR) to enhance the image perceptual quality. However, these generative models are prone to generating visual artifacts and false image structures, resulting in unnatural Real-ISR results. Based on the fact that natural images exhibit high self-similarities, i.e., a local patch can have many similar patches to it in the whole image, in this work we propose a simple yet effective self-similarity loss (SSL) to improve the performance of generative Real-ISR models, enhancing the hallucination of structural and textural details while reducing the unpleasant visual artifacts. Specifically, we compute a self-similarity graph (SSG) of the ground-truth image, and enforce the SSG of Real-ISR output to be close to it. To reduce the training cost and focus on edge areas, we generate an edge mask from the ground-truth image, and compute the SSG only on the masked pixels. The proposed SSL serves as a general plug-and-play penalty, which could be easily applied to the off-the-shelf Real-ISR models. Our experiments demonstrate that, by coupling with SSL, the performance of many state-of-the-art Real-ISR models, including those GAN and DM based ones, can be largely improved, reproducing more perceptually realistic image details and eliminating many false reconstructions and visual artifacts. Codes and supplementary material can be found at https://github.com/ChrisDud0257/SSL

cs.CV↗

arXiv2024

Dense Multimodal Alignment for Open-Vocabulary 3D Scene Understanding

Recent vision-language pre-training models have exhibited remarkable generalization ability in zero-shot recognition tasks. Previous open-vocabulary 3D scene understanding methods mostly focus on training 3D models using either image or text supervision while neglecting the collective strength of all modalities. In this work, we propose a Dense Multimodal Alignment (DMA) framework to densely co-embed different modalities into a common space for maximizing their synergistic benefits. Instead of extracting coarse view- or region-level text prompts, we leverage large vision-language models to extract complete category information and scalable scene descriptions to build the text modality, and take image modality as the bridge to build dense point-pixel-text associations. Besides, in order to enhance the generalization ability of the 2D model for downstream 3D tasks without compromising the open-vocabulary capability, we employ a dual-path integration approach to combine frozen CLIP visual features and learnable mask features. Extensive experiments show that our DMA method produces highly competitive open-vocabulary segmentation performance on various indoor and outdoor tasks.

cs.CV↗