arXiv:2607.02461v1 Announce Type: cross Abstract: Diffusion transformers (DiTs) achieve state-of-the-art image and video generation, but their multi-step sampling and growing parameter count make inference expensive. Post-training quantization (PTQ) is the natural remedy, yet DiT…
Diffusion transformers (DiTs) achieve state-of-the-art image and video generation, but their multi-step sampling and growing parameter count make inference expensive. Post-training quantization (PTQ) is the natural remedy, yet DiT activations shift across timesteps, prompts, and …
arXiv:2601.11641v3 Announce Type: replace-cross Abstract: While Diffusion Transformers (DiTs) have achieved notable progress in video generation, this long-sequence generation task remains constrained by the quadratic complexity inherent to self-attention mechanisms, creating sig…
arXiv:2606.31050v1 Announce Type: cross Abstract: How to accurately predict a high-fidelity future world? While the visual world is inherently continuous, existing deterministic video prediction models operate in discrete pixel space and are mainly optimized with pixel-wise mean …
arXiv:2403.07711v5 Announce Type: replace-cross Abstract: Given the remarkable achievements in image generation through diffusion models, the research community has shown increasing interest in extending these models to video generation. Recent diffusion models for video generati…
arXiv:2606.29095v1 Announce Type: cross Abstract: Diffusion-based video relighting enables controllable relighting from a single input video, but modern video diffusion backbones are trained on short clips and applied to long-horizon videos through chunked sliding-window inferenc…
ViDiHand uses pretrained video diffusion model representations with hand-overlay rendering to reconstruct 4D hand motion directly from video frames without detectors or optimization.
arXiv cs.CV
TIER_1English(EN)·Kyobin Choo, Youngmin Kim, Hyunkyung Han, Geunrip Park, Chanyoung Kim, Sunyoung Jung, Seong Jae Hwang·
arXiv:2607.01869v1 Announce Type: new Abstract: Video diffusion transformers (DiTs) generate high-fidelity and temporally coherent videos, yet motion control remains implicit, primarily relying on text prompts. As a result, achieving desired motion often requires extensive prompt…
arXiv:2607.01677v1 Announce Type: new Abstract: Monocular video depth estimation requires temporal consistency, geometric accuracy, and generalization across diverse scenarios, yet existing methods struggle to achieve all three simultaneously. Discriminative models excel at per-f…
arXiv cs.CV
TIER_1English(EN)·Edoardo A. Dominici, Thomas Deixelberger, Konstantinos Vardis, Markus Steinberger·
arXiv:2604.01761v2 Announce Type: replace Abstract: Video diffusion models have recently been applied with success to problems in content generation, novel view synthesis, and, more broadly, world simulation. Many applications in generation and transfer rely on conditioning these…
arXiv:2603.15129v3 Announce Type: replace Abstract: We present a novel paradigm for ultra-low-bitrate image compression (ULB-IC) that exploits the ``temporal'' evolution in generative image compression. Specifically, we define an explicit intermediate state during decoding: a com…
arXiv:2607.00987v1 Announce Type: new Abstract: Diffusion models have significantly advanced video super-resolution (VSR) but remain largely constrained to fixed upsampling scales. Conversely, while coordinate-based arbitrary-scale VSR methods offer scale flexibility, they inhere…
arXiv:2512.15702v2 Announce Type: replace Abstract: Autoregressive video diffusion models hold promise for world simulation but are vulnerable to exposure bias arising from the train-test mismatch. While recent works address this via post-training, they typically rely on a bidire…
Diffusion models have significantly advanced video super-resolution (VSR) but remain largely constrained to fixed upsampling scales. Conversely, while coordinate-based arbitrary-scale VSR methods offer scale flexibility, they inherently suffer from severe over-smoothing at large …
arXiv:2606.30308v1 Announce Type: new Abstract: 4D hand motion reconstruction from egocentric video is bottlenecked by clear limitations of existing methods: image-based pipelines depend on a detector that fails under heavy occlusion, while video-based methods rely on temporal mo…
arXiv:2508.14483v4 Announce Type: replace Abstract: We present Vivid-VR, a DiT-based generative video restoration method built upon an advanced T2V foundation model, where ControlNet is leveraged to control the generation process, ensuring content consistency. However, convention…
arXiv:2512.20606v2 Announce Type: replace Abstract: Despite achieving strong results on standard benchmarks, current point tracking methods rely on feature backbones that are rarely designed with the temporal coherence needed for robust real-world performance. While recent works …
arXiv:2603.14526v2 Announce Type: replace Abstract: The recent success of inference-time scaling in large language models has inspired similar explorations in video diffusion. In particular, motivated by the existence of "golden noise" that enhances video quality, prior work has …
arXiv:2606.28677v1 Announce Type: new Abstract: While diffusion models excel in video restoration, their reliance on extensive iterative steps limits efficiency. Conversely, aggressive single-step distillation often compromises fine texture recovery. To achieve an optimal balance…
4D hand motion reconstruction from egocentric video is bottlenecked by clear limitations of existing methods: image-based pipelines depend on a detector that fails under heavy occlusion, while video-based methods rely on temporal modules learned only from scarce hand-pose annotat…
arXiv cs.CV
TIER_1English(EN)·Xi Ye, Wenjia Yang, Yangyang Xu, Xiaoyang Liu, Duo Su, Mengfei Xia, Jun Zhu·
arXiv:2603.17426v2 Announce Type: replace Abstract: Image-conditioned video diffusion models achieve impressive visual realism but often suffer from weakened motion fidelity, e.g., reduced motion dynamics or degraded long-term temporal coherence, especially after fine-tuning. We …
arXiv:2606.27741v1 Announce Type: new Abstract: Recent advances in video diffusion models have greatly improved visual fidelity, yet their generated motions often violate physical plausibility. We observe a common kinematic failure, "motion entanglement", the unintended coupling …
Recent advances in video diffusion models have greatly improved visual fidelity, yet their generated motions often violate physical plausibility. We observe a common kinematic failure, "motion entanglement", the unintended coupling of independent motion sources, such as camera mo…
