arXiv subjects

Gim Hee Lee

Publications and source records attributed to Gim Hee Lee.

At least 55 records · Page 3Linked to original sources

arXiv2025

CLAIR: CLIP-Aided Weakly Supervised Zero-Shot Cross-Domain Image Retrieval

The recent growth of large foundation models that can easily generate pseudo-labels for huge quantity of unlabeled data makes unsupervised Zero-Shot Cross-Domain Image Retrieval (UZS-CDIR) less relevant. In this paper, we therefore turn our attention to weakly supervised ZS-CDIR (WSZS-CDIR) with noisy pseudo labels generated by large foundation models such as CLIP. To this end, we propose CLAIR to refine the noisy pseudo-labels with a confidence score from the similarity between the CLIP text and image features. Furthermore, we design inter-instance and inter-cluster contrastive losses to encode images into a class-aware latent space, and an inter-domain contrastive loss to alleviate domain discrepancies. We also learn a novel cross-domain mapping function in closed-form, using only CLIP text embeddings to project image features from one domain to another, thereby further aligning the image features for retrieval. Finally, we enhance the zero-shot generalization ability of our CLAIR to handle novel categories by introducing an extra set of learnable prompts. Extensive experiments are carried out using TUBerlin, Sketchy, Quickdraw, and DomainNet zero-shot datasets, where our CLAIR consistently shows superior performance compared to existing state-of-the-art methods.

cs.CV↗

arXiv2025

Statistical Confidence Rescoring for Robust 3D Scene Graph Generation from Multi-View Images

Modern 3D semantic scene graph estimation methods utilize ground truth 3D annotations to accurately predict target objects, predicates, and relationships. In the absence of given 3D ground truth representations, we explore leveraging only multi-view RGB images to tackle this task. To attain robust features for accurate scene graph estimation, we must overcome the noisy reconstructed pseudo point-based geometry from predicted depth maps and reduce the amount of background noise present in multi-view image features. The key is to enrich node and edge features with accurate semantic and spatial information and through neighboring relations. We obtain semantic masks to guide feature aggregation to filter background features and design a novel method to incorporate neighboring node information to aid robustness of our scene graph estimates. Furthermore, we leverage on explicit statistical priors calculated from the training summary statistics to refine node and edge predictions based on their one-hop neighborhood. Our experiments show that our method outperforms current methods purely using multi-view images as the initial input. Our project page is available at https://qixun1.github.io/projects/SCRSSG.

cs.CV↗

arXiv2025

Reconstructing Close Human Interaction with Appearance and Proxemics Reasoning

Due to visual ambiguities and inter-person occlusions, existing human pose estimation methods cannot recover plausible close interactions from in-the-wild videos. Even state-of-the-art large foundation models~(\eg, SAM) cannot accurately distinguish human semantics in such challenging scenarios. In this work, we find that human appearance can provide a straightforward cue to address these obstacles. Based on this observation, we propose a dual-branch optimization framework to reconstruct accurate interactive motions with plausible body contacts constrained by human appearances, social proxemics, and physical laws. Specifically, we first train a diffusion model to learn the human proxemic behavior and pose prior knowledge. The trained network and two optimizable tensors are then incorporated into a dual-branch optimization framework to reconstruct human motions and appearances. Several constraints based on 3D Gaussians, 2D keypoints, and mesh penetrations are also designed to assist the optimization. With the proxemics prior and diverse constraints, our method is capable of estimating accurate interactions from in-the-wild videos captured in complex environments. We further build a dataset with pseudo ground-truth interaction annotations, which may promote future research on pose estimation and human behavior understanding. Experimental results on several benchmarks demonstrate that our method outperforms existing approaches. The code and data are available at https://www.buzhenhuang.com/works/CloseApp.html.

cs.CV↗

arXiv2025

STD-GS: Exploring Frame-Event Interaction for SpatioTemporal-Disentangled Gaussian Splatting to Reconstruct High-Dynamic Scene

High-dynamic scene reconstruction aims to represent static background with rigid spatial features and dynamic objects with deformed continuous spatiotemporal features. Typically, existing methods adopt unified representation model (e.g., Gaussian) to directly match the spatiotemporal features of dynamic scene from frame camera. However, this unified paradigm fails in the potential discontinuous temporal features of objects due to frame imaging and the heterogeneous spatial features between background and objects. To address this issue, we disentangle the spatiotemporal features into various latent representations to alleviate the spatiotemporal mismatching between background and objects. In this work, we introduce event camera to compensate for frame camera, and propose a spatiotemporal-disentangled Gaussian splatting framework for high-dynamic scene reconstruction. As for dynamic scene, we figure out that background and objects have appearance discrepancy in frame-based spatial features and motion discrepancy in event-based temporal features, which motivates us to distinguish the spatiotemporal features between background and objects via clustering. As for dynamic object, we discover that Gaussian representations and event data share the consistent spatiotemporal characteristic, which could serve as a prior to guide the spatiotemporal disentanglement of object Gaussians. Within Gaussian splatting framework, the cumulative scene-object disentanglement can improve the spatiotemporal discrimination between background and objects to render the time-continuous dynamic scene. Extensive experiments have been performed to verify the superiority of the proposed method.

cs.CV↗

arXiv2025

Event-Driven Dynamic Scene Depth Completion

Depth completion in dynamic scenes poses significant challenges due to rapid ego-motion and object motion, which can severely degrade the quality of input modalities such as RGB images and LiDAR measurements. Conventional RGB-D sensors often struggle to align precisely and capture reliable depth under such conditions. In contrast, event cameras with their high temporal resolution and sensitivity to motion at the pixel level provide complementary cues that are %particularly beneficial in dynamic environments.To this end, we propose EventDC, the first event-driven depth completion framework. It consists of two key components: Event-Modulated Alignment (EMA) and Local Depth Filtering (LDF). Both modules adaptively learn the two fundamental components of convolution operations: offsets and weights conditioned on motion-sensitive event streams. In the encoder, EMA leverages events to modulate the sampling positions of RGB-D features to achieve pixel redistribution for improved alignment and fusion. In the decoder, LDF refines depth estimations around moving objects by learning motion-aware masks from events. Additionally, EventDC incorporates two loss terms to further benefit global alignment and enhance local depth recovery. Moreover, we establish the first benchmark for event-based depth completion comprising one real-world and two synthetic datasets to facilitate future research. Extensive experiments on this benchmark demonstrate the superiority of our EventDC.

cs.CV↗

arXiv2025

LLaVA-4D: Embedding SpatioTemporal Prompt into LMMs for 4D Scene Understanding

Despite achieving significant progress in 2D image understanding, large multimodal models (LMMs) struggle in the physical world due to the lack of spatial representation. Typically, existing 3D LMMs mainly embed 3D positions as fixed spatial prompts within visual features to represent the scene. However, these methods are limited to understanding the static background and fail to capture temporally varying dynamic objects. In this paper, we propose LLaVA-4D, a general LMM framework with a novel spatiotemporal prompt for visual representation in 4D scene understanding. The spatiotemporal prompt is generated by encoding 3D position and 1D time into a dynamic-aware 4D coordinate embedding. Moreover, we demonstrate that spatial and temporal components disentangled from visual features are more effective in distinguishing the background from objects. This motivates embedding the 4D spatiotemporal prompt into these features to enhance the dynamic scene representation. By aligning visual spatiotemporal embeddings with language embeddings, LMMs gain the ability to understand both spatial and temporal characteristics of static background and dynamic objects in the physical world. Additionally, we construct a 4D vision-language dataset with spatiotemporal coordinate annotations for instruction fine-tuning LMMs. Extensive experiments have been conducted to demonstrate the effectiveness of our method across different tasks in 4D scene understanding.

cs.CV↗

arXiv2025

Dynam3D: Dynamic Layered 3D Tokens Empower VLM for Vision-and-Language Navigation

Vision-and-Language Navigation (VLN) is a core task where embodied agents leverage their spatial mobility to navigate in 3D environments toward designated destinations based on natural language instructions. Recently, video-language large models (Video-VLMs) with strong generalization capabilities and rich commonsense knowledge have shown remarkable performance when applied to VLN tasks. However, these models still encounter the following challenges when applied to real-world 3D navigation: 1) Insufficient understanding of 3D geometry and spatial semantics; 2) Limited capacity for large-scale exploration and long-term environmental memory; 3) Poor adaptability to dynamic and changing environments.To address these limitations, we propose Dynam3D, a dynamic layered 3D representation model that leverages language-aligned, generalizable, and hierarchical 3D representations as visual input to train 3D-VLM in navigation action prediction. Given posed RGB-D images, our Dynam3D projects 2D CLIP features into 3D space and constructs multi-level 3D patch-instance-zone representations for 3D geometric and semantic understanding with a dynamic and layer-wise update strategy. Our Dynam3D is capable of online encoding and localization of 3D instances, and dynamically updates them in changing environments to provide large-scale exploration and long-term memory capabilities for navigation. By leveraging large-scale 3D-language pretraining and task-specific adaptation, our Dynam3D sets new state-of-the-art performance on VLN benchmarks including R2R-CE, REVERIE-CE and NavRAG-CE under monocular settings. Furthermore, experiments for pre-exploration, lifelong memory, and real-world robot validate the effectiveness of practical deployment.

cs.CV↗

arXiv2025

Generalizable Human Gaussians from Single-View Image

In this work, we tackle the task of learning 3D human Gaussians from a single image, focusing on recovering detailed appearance and geometry including unobserved regions. We introduce a single-view generalizable Human Gaussian Model (HGM), which employs a novel generate-then-refine pipeline with the guidance from human body prior and diffusion prior. Our approach uses a ControlNet to refine rendered back-view images from coarse predicted human Gaussians, then uses the refined image along with the input image to reconstruct refined human Gaussians. To mitigate the potential generation of unrealistic human poses and shapes, we incorporate human priors from the SMPL-X model as a dual branch, propagating image features from the SMPL-X volume to the image Gaussians using sparse convolution and attention mechanisms. Given that the initial SMPL-X estimation might be inaccurate, we gradually refine it with our HGM model. We validate our approach on several publicly available datasets. Our method surpasses previous methods in both novel view synthesis and surface reconstruction. Our approach also exhibits strong generalization for cross-dataset evaluation and in-the-wild images.

cs.CV↗

arXiv2025

MAR-3D: Progressive Masked Auto-regressor for High-Resolution 3D Generation

Recent advances in auto-regressive transformers have revolutionized generative modeling across different domains, from language processing to visual generation, demonstrating remarkable capabilities. However, applying these advances to 3D generation presents three key challenges: the unordered nature of 3D data conflicts with sequential next-token prediction paradigm, conventional vector quantization approaches incur substantial compression loss when applied to 3D meshes, and the lack of efficient scaling strategies for higher resolution latent prediction. To address these challenges, we introduce MAR-3D, which integrates a pyramid variational autoencoder with a cascaded masked auto-regressive transformer (Cascaded MAR) for progressive latent upscaling in the continuous space. Our architecture employs random masking during training and auto-regressive denoising in random order during inference, naturally accommodating the unordered property of 3D latent tokens. Additionally, we propose a cascaded training strategy with condition augmentation that enables efficiently up-scale the latent token resolution with fast convergence. Extensive experiments demonstrate that MAR-3D not only achieves superior performance and generalization capabilities compared to existing methods but also exhibits enhanced scaling capabilities compared to joint distribution modeling approaches (e.g., diffusion transformers).

cs.CV↗

arXiv2025

IAAO: Interactive Affordance Learning for Articulated Objects in 3D Environments

This work presents IAAO, a novel framework that builds an explicit 3D model for intelligent agents to gain understanding of articulated objects in their environment through interaction. Unlike prior methods that rely on task-specific networks and assumptions about movable parts, our IAAO leverages large foundation models to estimate interactive affordances and part articulations in three stages. We first build hierarchical features and label fields for each object state using 3D Gaussian Splatting (3DGS) by distilling mask features and view-consistent labels from multi-view images. We then perform object- and part-level queries on the 3D Gaussian primitives to identify static and articulated elements, estimating global transformations and local articulation parameters along with affordances. Finally, scenes from different states are merged and refined based on the estimated transformations, enabling robust affordance-based interaction and manipulation of objects. Experimental results demonstrate the effectiveness of our method.

cs.CV↗

arXiv2025

econSG: Efficient and Multi-view Consistent Open-Vocabulary 3D Semantic Gaussians

The primary focus of most recent works on open-vocabulary neural fields is extracting precise semantic features from the VLMs and then consolidating them efficiently into a multi-view consistent 3D neural fields representation. However, most existing works over-trusted SAM to regularize image-level CLIP without any further refinement. Moreover, several existing works improved efficiency by dimensionality reduction of semantic features from 2D VLMs before fusing with 3DGS semantic fields, which inevitably leads to multi-view inconsistency. In this work, we propose econSG for open-vocabulary semantic segmentation with 3DGS. Our econSG consists of: 1) A Confidence-region Guided Regularization (CRR) that mutually refines SAM and CLIP to get the best of both worlds for precise semantic features with complete and precise boundaries. 2) A low dimensional contextual space to enforce 3D multi-view consistency while improving computational efficiency by fusing backprojected multi-view 2D features and follow by dimensional reduction directly on the fused 3D features instead of operating on each 2D view separately. Our econSG shows state-of-the-art performance on four benchmark datasets compared to the existing methods. Furthermore, we are also the most efficient training among all the methods.

cs.CV↗

arXiv2025

DiET-GS: Diffusion Prior and Event Stream-Assisted Motion Deblurring 3D Gaussian Splatting

Reconstructing sharp 3D representations from blurry multi-view images are long-standing problem in computer vision. Recent works attempt to enhance high-quality novel view synthesis from the motion blur by leveraging event-based cameras, benefiting from high dynamic range and microsecond temporal resolution. However, they often reach sub-optimal visual quality in either restoring inaccurate color or losing fine-grained details. In this paper, we present DiET-GS, a diffusion prior and event stream-assisted motion deblurring 3DGS. Our framework effectively leverages both blur-free event streams and diffusion prior in a two-stage training strategy. Specifically, we introduce the novel framework to constraint 3DGS with event double integral, achieving both accurate color and well-defined details. Additionally, we propose a simple technique to leverage diffusion prior to further enhance the edge details. Qualitative and quantitative results on both synthetic and real-world data demonstrate that our DiET-GS is capable of producing significantly better quality of novel views compared to the existing baselines. Our project page is https://diet-gs.github.io

cs.CV↗

arXiv2025

DiHuR: Diffusion-Guided Generalizable Human Reconstruction

We introduce DiHuR, a novel Diffusion-guided model for generalizable Human 3D Reconstruction and view synthesis from sparse, minimally overlapping images. While existing generalizable human radiance fields excel at novel view synthesis, they often struggle with comprehensive 3D reconstruction. Similarly, directly optimizing implicit Signed Distance Function (SDF) fields from sparse-view images typically yields poor results due to limited overlap. To enhance 3D reconstruction quality, we propose using learnable tokens associated with SMPL vertices to aggregate sparse view features and then to guide SDF prediction. These tokens learn a generalizable prior across different identities in training datasets, leveraging the consistent projection of SMPL vertices onto similar semantic areas across various human identities. This consistency enables effective knowledge transfer to unseen identities during inference. Recognizing SMPL's limitations in capturing clothing details, we incorporate a diffusion model as an additional prior to fill in missing information, particularly for complex clothing geometries. Our method integrates two key priors in a coherent manner: the prior from generalizable feed-forward models and the 2D diffusion prior, and it requires only multi-view image training, without 3D supervision. DiHuR demonstrates superior performance in both within-dataset and cross-dataset generalization settings, as validated on THuman, ZJU-MoCap, and HuMMan datasets compared to existing methods.

cs.CV↗

arXiv2025

FreeSplat++: Generalizable 3D Gaussian Splatting for Efficient Indoor Scene Reconstruction

Recently, the integration of the efficient feed-forward scheme into 3D Gaussian Splatting (3DGS) has been actively explored. However, most existing methods focus on sparse view reconstruction of small regions and cannot produce eligible whole-scene reconstruction results in terms of either quality or efficiency. In this paper, we propose FreeSplat++, which focuses on extending the generalizable 3DGS to become an alternative approach to large-scale indoor whole-scene reconstruction, which has the potential of significantly accelerating the reconstruction speed and improving the geometric accuracy. To facilitate whole-scene reconstruction, we initially propose the Low-cost Cross-View Aggregation framework to efficiently process extremely long input sequences. Subsequently, we introduce a carefully designed pixel-wise triplet fusion method to incrementally aggregate the overlapping 3D Gaussian primitives from multiple views, adaptively reducing their redundancy. Furthermore, we propose a weighted floater removal strategy that can effectively reduce floaters, which serves as an explicit depth fusion approach that is crucial in whole-scene reconstruction. After the feed-forward reconstruction of 3DGS primitives, we investigate a depth-regularized per-scene fine-tuning process. Leveraging the dense, multi-view consistent depth maps obtained during the feed-forward prediction phase for an extra constraint, we refine the entire scene's 3DGS primitive to enhance rendering quality while preserving geometric accuracy. Extensive experiments confirm that our FreeSplat++ significantly outperforms existing generalizable 3DGS methods, especially in whole-scene reconstructions. Compared to conventional per-scene optimized 3DGS approaches, our method with depth-regularized per-scene fine-tuning demonstrates substantial improvements in reconstruction accuracy and a notable reduction in training time.

cs.CV↗

arXiv2025

Learnable Infinite Taylor Gaussian for Dynamic View Rendering

Capturing the temporal evolution of Gaussian properties such as position, rotation, and scale is a challenging task due to the vast number of time-varying parameters and the limited photometric data available, which generally results in convergence issues, making it difficult to find an optimal solution. While feeding all inputs into an end-to-end neural network can effectively model complex temporal dynamics, this approach lacks explicit supervision and struggles to generate high-quality transformation fields. On the other hand, using time-conditioned polynomial functions to model Gaussian trajectories and orientations provides a more explicit and interpretable solution, but requires significant handcrafted effort and lacks generalizability across diverse scenes. To overcome these limitations, this paper introduces a novel approach based on a learnable infinite Taylor Formula to model the temporal evolution of Gaussians. This method offers both the flexibility of an implicit network-based approach and the interpretability of explicit polynomial functions, allowing for more robust and generalizable modeling of Gaussian dynamics across various dynamic scenes. Extensive experiments on dynamic novel view rendering tasks are conducted on public datasets, demonstrating that the proposed method achieves state-of-the-art performance in this domain. More information is available on our project page(https://ellisonking.github.io/TaylorGaussian).

cs.CV↗

arXiv2025

Unified Geometry and Color Compression Framework for Point Clouds via Generative Diffusion Priors

With the growth of 3D applications and the rapid increase in sensor-collected 3D point cloud data, there is a rising demand for efficient compression algorithms. Most existing learning-based compression methods handle geometry and color attributes separately, treating them as distinct tasks, making these methods challenging to apply directly to point clouds with colors. Besides, the limited capacities of training datasets also limit their generalizability across points with different distributions. In this work, we introduce a test-time unified geometry and color compression framework of 3D point clouds. Instead of training a compression model based on specific datasets, we adapt a pre-trained generative diffusion model to compress original colored point clouds into sparse sets, termed 'seeds', using prompt tuning. Decompression is then achieved through multiple denoising steps with separate sampling processes. Experiments on objects and indoor scenes demonstrate that our method has superior performances compared to existing baselines for the compression of geometry and color.

cs.CV↗

arXiv2025

NeuSG: Neural Implicit Surface Reconstruction with 3D Gaussian Splatting Guidance

Existing neural implicit surface reconstruction methods have achieved impressive performance in multi-view 3D reconstruction by leveraging explicit geometry priors such as depth maps or point clouds as regularization. However, the reconstruction results still lack fine details because of the over-smoothed depth map or sparse point cloud. In this work, we propose a neural implicit surface reconstruction pipeline with guidance from 3D Gaussian Splatting to recover highly detailed surfaces. The advantage of 3D Gaussian Splatting is that it can generate dense point clouds with detailed structure. Nonetheless, a naive adoption of 3D Gaussian Splatting can fail since the generated points are the centers of 3D Gaussians that do not necessarily lie on the surface. We thus introduce a scale regularizer to pull the centers close to the surface by enforcing the 3D Gaussians to be extremely thin. Moreover, we propose to refine the point cloud from 3D Gaussians Splatting with the normal priors from the surface predicted by neural implicit models instead of using a fixed set of points as guidance. Consequently, the quality of surface reconstruction improves from the guidance of the more accurate 3D Gaussian splatting. By jointly optimizing the 3D Gaussian Splatting and the neural implicit model, our approach benefits from both representations and generates complete surfaces with intricate details. Experiments on Tanks and Temples verify the effectiveness of our proposed method.

cs.CV↗

arXiv2025

TreeMeshGPT: Artistic Mesh Generation with Autoregressive Tree Sequencing

We introduce TreeMeshGPT, an autoregressive Transformer designed to generate high-quality artistic meshes aligned with input point clouds. Instead of the conventional next-token prediction in autoregressive Transformer, we propose a novel Autoregressive Tree Sequencing where the next input token is retrieved from a dynamically growing tree structure that is built upon the triangle adjacency of faces within the mesh. Our sequencing enables the mesh to extend locally from the last generated triangular face at each step, and therefore reduces training difficulty and improves mesh quality. Our approach represents each triangular face with two tokens, achieving a compression rate of approximately 22% compared to the naive face tokenization. This efficient tokenization enables our model to generate highly detailed artistic meshes with strong point cloud conditioning, surpassing previous methods in both capacity and fidelity. Furthermore, our method generates mesh with strong normal orientation constraints, minimizing flipped normals commonly encountered in previous methods. Our experiments show that TreeMeshGPT enhances the mesh generation quality with refined details and normal orientation consistency.

cs.GR↗