arXiv subjects

Seungryong Kim

Publications and source records attributed to Seungryong Kim.

At least 55 records · Page 3Linked to original sources

arXiv2026

TETO: Tracking Events with Teacher Observation for Motion Estimation and Frame Interpolation

Event cameras capture per-pixel brightness changes with microsecond resolution, offering continuous motion information lost between RGB frames. However, existing event-based motion estimators depend on large-scale synthetic data that often suffers from a significant sim-to-real gap. We propose TETO (Tracking Events with Teacher Observation), a teacher-student framework that learns event motion estimation from only $\sim$25 minutes of unannotated real-world recordings through knowledge distillation from a pretrained RGB tracker. Our motion-aware data curation and query sampling strategy maximizes learning from limited data by disentangling object motion from dominant ego-motion. The resulting estimator jointly predicts point trajectories and dense optical flow, which we leverage as explicit motion priors to condition a pretrained video diffusion transformer for frame interpolation. We achieve state-of-the-art point tracking on EVIMO2 and optical flow on DSEC using orders of magnitude less training data, and demonstrate that accurate motion estimation translates directly to superior frame interpolation quality on BS-ERGB and HQ-EVFI.

cs.CV↗

arXiv2026

AgentRVOS: Reasoning over Object Tracks for Zero-Shot Referring Video Object Segmentation

Referring Video Object Segmentation (RVOS) aims to segment a target object throughout a video given a natural language query. Training-free methods for this task follow a common pipeline: a MLLM selects keyframes, grounds the referred object within those frames, and a video segmentation model propagates the results. While intuitive, this design asks the MLLM to make temporal decisions before any object-level evidence is available, limiting both reasoning quality and spatio-temporal coverage. To overcome this, we propose AgentRVOS, a training-free agentic pipeline built on the complementary strengths of SAM3 and a MLLM. Given a concept derived from the query, SAM3 provides reliable perception over the full spatio-temporal extent through generated mask tracks. The MLLM then identifies the target through query-grounded reasoning over this object-level evidence, iteratively pruning guided by SAM3's temporal existence information. Extensive experiments show that AgentRVOS achieves state-of-the-art performance among training-free methods across multiple benchmarks, with consistent results across diverse MLLM backbones. Our project page is available at: https://cvlab-kaist.github.io/AgentRVOS/.

cs.CV↗

arXiv2026

DA-Flow: Degradation-Aware Optical Flow Estimation with Diffusion Models

Optical flow models trained on high-quality data often degrade severely when confronted with real-world corruptions such as blur, noise, and compression artifacts. To overcome this limitation, we formulate Degradation-Aware Optical Flow, a new task targeting accurate dense correspondence estimation from real-world corrupted videos. Our key insight is that the intermediate representations of image restoration diffusion models are inherently corruption-aware but lack temporal awareness. To address this limitation, we lift the model to attend across adjacent frames via full spatio-temporal attention, and empirically demonstrate that the resulting features exhibit zero-shot correspondence capabilities. Based on this finding, we present DA-Flow, a hybrid architecture that fuses these diffusion features with convolutional features within an iterative refinement framework. DA-Flow substantially outperforms existing optical flow methods under severe degradation across multiple benchmarks.

cs.CV↗

arXiv2026

Repurposing Geometric Foundation Models for Multi-view Diffusion

While recent advances in generative latent spaces have driven substantial progress in single-image generation, the optimal latent space for novel view synthesis (NVS) remains largely unexplored. In particular, NVS requires geometrically consistent generation across viewpoints, but existing approaches typically operate in a view-independent VAE latent space. In this paper, we propose Geometric Latent Diffusion (GLD), a framework that repurposes the geometrically consistent feature space of geometric foundation models as the latent space for multi-view diffusion. We show that these features not only support high-fidelity RGB reconstruction but also encode strong cross-view geometric correspondences, providing a well-suited latent space for NVS. Our experiments demonstrate that GLD outperforms both VAE and RAE on 2D image quality and 3D consistency metrics, while accelerating training by more than 4.4x compared to the VAE latent space. Notably, GLD remains competitive with state-of-the-art methods that leverage large-scale text-to-image pretraining, despite training its diffusion model from scratch without such generative pretraining.

cs.CV↗

arXiv2026

WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation

Recent advances in video diffusion transformers have enabled interactive gaming world models that allow users to explore generated environments over extended horizons. However, existing approaches struggle with precise action control and long-horizon 3D consistency. Most prior works treat user actions as abstract conditioning signals, overlooking the fundamental geometric coupling between actions and the 3D world, whereby actions induce relative camera motions that accumulate into a global camera pose within a 3D world. In this paper, we establish camera pose as a unifying geometric representation to jointly ground immediate action control and long-term 3D consistency. First, we define a physics-based continuous action space and represent user inputs in the Lie algebra to derive precise 6-DoF camera poses, which are injected into the generative model via a camera embedder to ensure accurate action alignment. Second, we use global camera poses as spatial indices to retrieve relevant past observations, enabling geometrically consistent revisiting of locations during long-horizon navigation. To support this research, we introduce a large-scale dataset comprising 3,000 minutes of authentic human gameplay annotated with camera trajectories and textual descriptions. Extensive experiments show that our approach substantially outperforms state-of-the-art interactive gaming world models in action controllability, long-horizon visual quality, and 3D spatial consistency.

cs.CV↗

arXiv2026

Grounding World Simulation Models in a Real-World Metropolis

What if a world simulation model could render not an imagined environment but a city that actually exists? Prior generative world models synthesize visually plausible yet artificial environments by imagining all content. We present Seoul World Model (SWM), a city-scale world model grounded in the real city of Seoul. SWM anchors autoregressive video generation through retrieval-augmented conditioning on nearby street-view images. However, this design introduces several challenges, including temporal misalignment between retrieved references and the dynamic target scene, limited trajectory diversity and data sparsity from vehicle-mounted captures at sparse intervals. We address these challenges through cross-temporal pairing, a large-scale synthetic dataset enabling diverse camera trajectories, and a view interpolation pipeline that synthesizes coherent training videos from sparse street-view images. We further introduce a Virtual Lookahead Sink to stabilize long-horizon generation by continuously re-grounding each chunk to a retrieved image at a future location. We evaluate SWM against recent video world models across three cities: Seoul, Busan, and Ann Arbor. SWM outperforms existing methods in generating spatially faithful, temporally consistent, long-horizon videos grounded in actual urban environments over trajectories reaching hundreds of meters, while supporting diverse camera movements and text-prompted scenario variations.

cs.CV↗

arXiv2026

Pri4R: Learning World Dynamics for Vision-Language-Action Models with Privileged 4D Representation

Humans learn not only how their bodies move, but also how the surrounding world responds to their actions. In contrast, while recent Vision-Language-Action (VLA) models exhibit impressive semantic understanding, they often fail to capture the spatiotemporal dynamics governing physical interaction. In this paper, we introduce Pri4R, a simple yet effective approach that endows VLA models with an implicit understanding of world dynamics by leveraging privileged 4D information during training. Specifically, Pri4R augments VLAs with a lightweight point track head that predicts 3D point tracks. By injecting VLA features into this head to jointly predict future 3D trajectories, the model learns to incorporate evolving scene geometry within its shared representation space, enabling more physically aware context for precise control. Due to its architectural simplicity, Pri4R is compatible with dominant VLA design patterns with minimal changes. During inference, we run the model using the original VLA architecture unchanged; Pri4R adds no extra inputs, outputs, or computational overhead. Across simulation and real-world evaluations, Pri4R significantly improves performance on challenging manipulation tasks, including a +10% gain on LIBERO-Long and a +40% gain on RoboCasa. We further show that 3D point track prediction is an effective supervision target for learning action-world dynamics, and validate our design choices through extensive ablations. Project page: https://jiiiisoo.github.io/Pri4R/

cs.CV↗

arXiv2026

CORAL: Correspondence Alignment for Improved Virtual Try-On

Existing methods for Virtual Try-On (VTON) often struggle to preserve fine garment details, especially in unpaired settings where accurate person-garment correspondence is required. These methods do not explicitly enforce person-garment alignment and fail to explain how correspondence emerges within Diffusion Transformers (DiTs). In this paper, we first analyze full 3D attention in DiT-based architecture and reveal that the person-garment correspondence critically depends on precise person-garment query-key matching within the full 3D attention. Building on this insight, we then introduce CORrespondence ALignment (CORAL), a DiT-based framework that explicitly aligns query-key matching with robust external correspondences. CORAL integrates two complementary components: a correspondence distillation loss that aligns reliable matches with person-garment attention, and an entropy minimization loss that sharpens the attention distribution. We further propose a VLM-based evaluation protocol to better reflect human preference. CORAL consistently improves over the baseline, enhancing both global shape transfer and local detail preservation. Extensive ablations validate our design choices.

cs.CV↗

arXiv2026

Projected Representation Conditioning for High-fidelity Novel View Synthesis

We propose a novel framework for diffusion-based novel view synthesis in which we leverage external representations as conditions, harnessing their geometric and semantic correspondence properties for enhanced geometric consistency in generated novel viewpoints. First, we provide a detailed analysis exploring the correspondence capabilities emergent in the spatial attention of external visual representations. Building from these insights, we propose a representation-guided novel view synthesis through dedicated representation projection modules that inject external representations into the diffusion process, a methodology named ReNoV, short for representation-guided novel view synthesis. Our experiments show that this design yields marked improvements in both reconstruction fidelity and inpainting quality, outperforming prior diffusion-based novel-view methods on standard benchmarks and enabling robust synthesis from sparse, unposed image collections.

cs.CV↗

arXiv2026

Aligned Novel View Image and Geometry Synthesis via Cross-modal Attention Instillation

We introduce a diffusion-based framework that performs aligned novel view image and geometry generation via a warping-and-inpainting methodology. Unlike prior methods that require dense posed images or pose-embedded generative models limited to in-domain views, our method leverages off-the-shelf geometry predictors to predict partial geometries viewed from reference images, and formulates novel-view synthesis as an inpainting task for both image and geometry. To ensure accurate alignment between generated images and geometry, we propose cross-modal attention distillation, where attention maps from the image diffusion branch are injected into a parallel geometry diffusion branch during both training and inference. This multi-task approach achieves synergistic effects, facilitating geometrically robust image synthesis as well as well-defined geometry prediction. We further introduce proximity-based mesh conditioning to integrate depth and normal cues, interpolating between point cloud and filtering erroneously predicted geometry from influencing the generation process. Empirically, our method achieves high-fidelity extrapolative view synthesis on both image and geometry across a range of unseen scenes, delivers competitive reconstruction quality under interpolation settings, and produces geometrically aligned colored point clouds for comprehensive 3D completion. Project page is available at https://cvlab-kaist.github.io/MoAI.

cs.CV↗

arXiv2026

VideoMaMa: Mask-Guided Video Matting via Generative Prior

Generalizing video matting models to real-world videos remains a significant challenge due to the scarcity of labeled data. To address this, we present Video Mask-to-Matte Model (VideoMaMa) that converts coarse segmentation masks into pixel accurate alpha mattes, by leveraging pretrained video diffusion models. VideoMaMa demonstrates strong zero-shot generalization to real-world footage, even though it is trained solely on synthetic data. Building on this capability, we develop a scalable pseudo-labeling pipeline for large-scale video matting and construct the Matting Anything in Video (MA-V) dataset, which offers high-quality matting annotations for more than 50K real-world videos spanning diverse scenes and motions. To validate the effectiveness of this dataset, we fine-tune the SAM2 model on MA-V to obtain SAM2-Matte, which outperforms the same model trained on existing matting datasets in terms of robustness on in-the-wild videos. These findings emphasize the importance of large-scale pseudo-labeled video matting and showcase how generative priors and accessible segmentation cues can drive scalable progress in video matting research.

cs.CV↗

arXiv2025

CorGi: Contribution-Guided Block-Wise Interval Caching for Training-Free Acceleration of Diffusion Transformers

Diffusion transformer (DiT) achieves remarkable performance in visual generation, but its iterative denoising process combined with larger capacity leads to a high inference cost. Recent works have demonstrated that the iterative denoising process of DiT models involves substantial redundant computation across steps. To effectively reduce the redundant computation in DiT, we propose CorGi (Contribution-Guided Block-Wise Interval Caching), training-free DiT inference acceleration framework that selectively reuses the outputs of transformer blocks in DiT across denoising steps. CorGi caches low-contribution blocks and reuses them in later steps within each interval to reduce redundant computation while preserving generation quality. For text-to-image tasks, we further propose CorGi+, which leverages per-block cross-attention maps to identify salient tokens and applies partial attention updates to protect important object details. Evaluation on the state-of-the-art DiT models demonstrates that CorGi and CorGi+ achieve up to 2.0x speedup on average, while preserving high generation quality.

cs.CV↗

arXiv2025

WaTeRFlow: Watermark Temporal Robustness via Flow Consistency

Image watermarking supports authenticity and provenance, yet many schemes are still easy to bypass with various distortions and powerful generative edits. Deep learning-based watermarking has improved robustness to diffusion-based image editing, but a gap remains when a watermarked image is converted to video by image-to-video (I2V), in which per-frame watermark detection weakens. I2V has quickly advanced from short, jittery clips to multi-second, temporally coherent scenes, and it now serves not only content creation but also world-modeling and simulation workflows, making cross-modal watermark recovery crucial. We present WaTeRFlow, a framework tailored for robustness under I2V. It consists of (i) FUSE (Flow-guided Unified Synthesis Engine), which exposes the encoder-decoder to realistic distortions via instruction-driven edits and a fast video diffusion proxy during training, (ii) optical-flow warping with a Temporal Consistency Loss (TCL) that stabilizes per-frame predictions, and (iii) a semantic preservation loss that maintains the conditioning signal. Experiments across representative I2V models show accurate watermark recovery from frames, with higher first-frame and per-frame bit accuracy and resilience when various distortions are applied before or after video generation.

cs.CV↗

arXiv2025

3D Scene Prompting for Scene-Consistent Camera-Controllable Video Generation

We present 3DScenePrompt, a framework that generates the next video chunk from arbitrary-length input while enabling precise camera control and preserving scene consistency. Unlike methods conditioned on a single image or a short clip, we employ dual spatio-temporal conditioning that reformulates context-view referencing across the input video. Our approach conditions on both temporally adjacent frames for motion continuity and spatially adjacent content for scene consistency. However, when generating beyond temporal boundaries, directly using spatially adjacent frames would incorrectly preserve dynamic elements from the past. We address this by introducing a 3D scene memory that represents exclusively the static geometry extracted from the entire input video. To construct this memory, we leverage dynamic SLAM with our newly introduced dynamic masking strategy that explicitly separates static scene geometry from moving elements. The static scene representation can then be projected to any target viewpoint, providing geometrically consistent warped views that serve as strong 3D spatial prompts while allowing dynamic regions to evolve naturally from temporal context. This enables our model to maintain long-range spatial coherence and precise camera control without sacrificing computational efficiency or motion realism. Extensive experiments demonstrate that our framework significantly outperforms existing methods in scene consistency, camera controllability, and generation quality. Project page : https://cvlab-kaist.github.io/3DScenePrompt/

cs.CV↗

arXiv2025

V-Warper: Appearance-Consistent Video Diffusion Personalization via Value Warping

Video personalization aims to generate videos that faithfully reflect a user-provided subject while following a text prompt. However, existing approaches often rely on heavy video-based finetuning or large-scale video datasets, which impose substantial computational cost and are difficult to scale. Furthermore, they still struggle to maintain fine-grained appearance consistency across frames. To address these limitations, we introduce V-Warper, a training-free coarse-to-fine personalization framework for transformer-based video diffusion models. The framework enhances fine-grained identity fidelity without requiring any additional video training. (1) A lightweight coarse appearance adaptation stage leverages only a small set of reference images, which are already required for the task. This step encodes global subject identity through image-only LoRA and subject-embedding adaptation. (2) A inference-time fine appearance injection stage refines visual fidelity by computing semantic correspondences from RoPE-free mid-layer query--key features. These correspondences guide the warping of appearance-rich value representations into semantically aligned regions of the generation process, with masking ensuring spatial reliability. V-Warper significantly improves appearance fidelity while preserving prompt alignment and motion dynamics, and it achieves these gains efficiently without large-scale video finetuning.

cs.CV↗

arXiv2025

Unified Diffusion Transformer for High-fidelity Text-Aware Image Restoration

Text-Aware Image Restoration (TAIR) aims to recover high-quality images from low-quality inputs containing degraded textual content. While diffusion models provide strong generative priors for general image restoration, they often produce text hallucinations in text-centric tasks due to the absence of explicit linguistic knowledge. To address this, we propose UniT, a unified text restoration framework that integrates a Diffusion Transformer (DiT), a Vision-Language Model (VLM), and a Text Spotting Module (TSM) in an iterative fashion for high-fidelity text restoration. In UniT, the VLM extracts textual content from degraded images to provide explicit textual guidance. Simultaneously, the TSM, trained on diffusion features, generates intermediate OCR predictions at each denoising step, enabling the VLM to iteratively refine its guidance during the denoising process. Finally, the DiT backbone, leveraging its strong representational power, exploit these cues to recover fine-grained textual content while effectively suppressing text hallucinations. Experiments on the SA-Text and Real-Text benchmarks demonstrate that UniT faithfully reconstructs degraded text, substantially reduces hallucinations, and achieves state-of-the-art end-to-end F1-score performance in TAIR task.

cs.CV↗

arXiv2025

First Attentions Last: Better Exploiting First Attentions for Efficient Transformer Training

As training billion-scale transformers becomes increasingly common, employing multiple distributed GPUs along with parallel training methods has become a standard practice. However, existing transformer designs suffer from significant communication overhead, especially in Tensor Parallelism (TP), where each block's MHA-MLP connection requires an all-reduce communication. Through our investigation, we show that the MHA-MLP connections can be bypassed for efficiency, while the attention output of the first layer can serve as an alternative signal for the bypassed connection. Motivated by the observations, we propose FAL (First Attentions Last), an efficient transformer architecture that redirects the first MHA output to the MLP inputs of the following layers, eliminating the per-block MHA-MLP connections. This removes the all-reduce communication and enables parallel execution of MHA and MLP on a single GPU. We also introduce FAL+, which adds the normalized first attention output to the MHA outputs of the following layers to augment the MLP input for the model quality. Our evaluation shows that FAL reduces multi-GPU training time by up to 44%, improves single-GPU throughput by up to 1.18x, and achieves better perplexity compared to the baseline GPT. FAL+ achieves even lower perplexity without increasing the training time than the baseline. Codes are available at: https://github.com/CASL-KU/FAL

cs.LG↗

arXiv2025

Deep Forcing: Training-Free Long Video Generation with Deep Sink and Participative Compression

Recent advances in autoregressive video diffusion have enabled real-time frame streaming, yet existing solutions still suffer from temporal repetition, drift, and motion deceleration. We find that naively applying StreamingLLM-style attention sinks to video diffusion leads to fidelity degradation and motion stagnation. To overcome this, we introduce Deep Forcing, which consists of two training-free mechanisms that address this without any fine-tuning. Specifically, 1) Deep Sink dedicates half of the sliding window to persistent sink tokens and re-aligns their temporal RoPE phase to the current timeline, stabilizing global context during long rollouts. 2) Participative Compression performs importance-aware KV cache pruning that preserves only tokens actively participating in recent attention while safely discarding redundant and degraded history, minimizing error accumulation under out-of-distribution length generation. Together, these components enable over 12x extrapolation (e.g. 5s-trained to 60s+ generation) with better imaging quality than LongLive, better aesthetic quality than RollingForcing, almost maintaining overall consistency, and substantial gains in dynamic degree, all while maintaining real-time generation. Our results demonstrate that training-free KV-cache management can match or exceed training-based approaches for autoregressively streaming long-video generation.

cs.CV↗