57 citations · 130 across the 55 of their papers we have counts for
63 papers
In-Flight KV Cache with Clean Anchors for Faster Autoregressive Video Diffusion
Yikai Wang, Xiao Han, Mengmeng Xu +9
Few-step autoregressive video diffusion generates a long video by splitting the video into temporal chunks and generating chunk-by-chunk, each through a short sequence of denoising…
Puffin-World: Scaling a Unified Multimodal Model with Native 3D World States
Kang Liao, Yihang Luo, Xiao-Ming Wu +7
We propose Puffin-World, a unified multimodal architecture that integrates physical understanding, spatial simulation, and 3D world generation and reconstruction without relying on…
AnyBokeh: Physics-Guided Any-to-Any Bokeh Editing with Optical Fingerprint Transfer
Xinyu Hou, Xiaoming Li, Zongsheng Yue +1
Depth-of-field control is a fundamental tool in photography, yet post-capture bokeh editing from a single image remains challenging. A practical editor should handle images capture…
Generate Your Talking Avatar from Video Reference
Zujin Guo, Zhenhui Ye, Yi Ren +4
Existing talking avatar methods typically adopt an image-to-video pipeline conditioned on a static reference image within the same scene as the target generation. This restricted,…
Zoom-IQA: Image Quality Assessment with Reliable Region-Aware Reasoning
Guoqiang Liang, Jianyi Wang, Zhonghua Wu +2
Image Quality Assessment (IQA) is a long-standing problem in computer vision. Previous methods typically focus on predicting numerical scores without explanation or providing low-l…
Generative Photographic Control for Scene-Consistent Video Cinematic Editing
Huiqiang Sun, Liao Shen, Zhan Peng +9
Cinematic storytelling is profoundly shaped by the artful manipulation of photographic elements such as depth of field and exposure. These effects are crucial in conveying mood and…
Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation
Kang Liao, Size Wu, Zhonghua Wu +6
Camera-centric understanding and generation are two cornerstones of spatial intelligence, yet they are typically studied in isolation. We present Puffin, a unified camera-centric m…
Half-Physics: Enabling Kinematic 3D Human Model with Physical Interactions
Li Siyao, Yao Feng, Omid Taheri +2
While current general-purpose 3D human models (e.g., SMPL-X) efficiently represent accurate human shape and pose, they lacks the ability to physically interact with the environment…
Enhanced Generative Structure Prior for Chinese Text Image Super-resolution
Xiaoming Li, Wangmeng Zuo, Chen Change Loy
Faithful text image super-resolution (SR) is challenging because each character has a unique structure and usually exhibits diverse font styles and layouts. While existing methods…
Next Visual Granularity Generation
Yikai Wang, Zhouxia Wang, Zhonghua Wu +3
We propose a novel approach to image generation by decomposing an image into a structured sequence, where each element in the sequence shares the same spatial resolution but differ…
SA-LUT: Spatial Adaptive 4D Look-Up Table for Photorealistic Style Transfer
Zerui Gong, Zhonghua Wu, Qingyi Tao +2
Photorealistic style transfer (PST) enables real-world color grading by adapting reference image colors while preserving content structure. Existing methods mainly follow either ap…
OpenUni: A Simple Baseline for Unified Multimodal Understanding and Generation
Size Wu, Zhonghua Wu, Zerui Gong +5
In this report, we present OpenUni, a simple, lightweight, and fully open-source baseline for unifying multimodal understanding and generation. Inspired by prevailing practices in…
SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training
Jianyi Wang, Shanchuan Lin, Zhijie Lin +10
Recent advances in diffusion-based video restoration (VR) demonstrate significant improvement in visual quality, yet yield a prohibitive computational cost during inference. While…
Controllable Human-centric Keyframe Interpolation with Generative Prior
Zujin Guo, Size Wu, Zhongang Cai +2
Existing interpolation methods use pre-trained video diffusion priors to generate intermediate frames between sparsely sampled keyframes. In the absence of 3D geometric guidance, t…
Harmonizing Visual Representations for Unified Multimodal Understanding and Generation
Size Wu, Wenwei Zhang, Lumin Xu +6
Unifying visual understanding and generation within a single multimodal framework remains a significant challenge, as the two inherently heterogeneous tasks require representations…
DoF-Gaussian: Controllable Depth-of-Field for 3D Gaussian Splatting
Liao Shen, Tianqi Liu, Huiqiang Sun +4
Recent advances in 3D Gaussian Splatting (3D-GS) have shown remarkable success in representing 3D scenes and generating high-quality, novel views in real-time. However, 3D-GS and i…
MEAT: Multiview Diffusion Model for Human Generation on Megapixels with Mesh Attention
Yuhan Wang, Fangzhou Hong, Shuai Yang +3
Multiview diffusion models have shown considerable success in image-to-3D generation for general objects. However, when applied to human data, existing methods have yet to deliver…
SMPLest-X: Ultimate Scaling for Expressive Human Pose and Shape Estimation
Wanqi Yin, Zhongang Cai, Ruisi Wang +12
Expressive human pose and shape estimation (EHPS) unifies body, hands, and face motion capture with numerous applications. Despite encouraging progress, current state-of-the-art me…
MatAnyone: Stable Video Matting with Consistent Memory Propagation
Peiqing Yang, Shangchen Zhou, Jixin Zhao +2
Auxiliary-free human video matting methods, which rely solely on input frames, often struggle with complex or ambiguous backgrounds. To address this, we propose MatAnyone, a robust…
SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restoration
Jianyi Wang, Zhijie Lin, Meng Wei +5
Video restoration poses non-trivial challenges in maintaining fidelity while recovering temporally consistent details from unknown degradations in the wild. Despite recent advances…
3DEnhancer: Consistent Multi-View Diffusion for 3D Enhancement
Yihang Luo, Shangchen Zhou, Yushi Lan +2
Despite advances in neural rendering, due to the scarcity of high-quality 3D datasets and the inherent limitations of multi-view diffusion models, view synthesis and 3D model gener…
Arbitrary-steps Image Super-resolution via Diffusion Inversion
Zongsheng Yue, Kang Liao, Chen Change Loy
This study presents a new image super-resolution (SR) technique based on diffusion inversion, aiming at harnessing the rich image priors encapsulated in large pre-trained diffusion…
ObjCtrl-2.5D: Training-free Object Control with Camera Poses
Zhouxia Wang, Yushi Lan, Shangchen Zhou +1
This study aims to achieve more precise and versatile object control in image-to-video (I2V) generation. Current methods typically represent the spatial movement of target objects…
Omegance: A Single Parameter for Various Granularities in Diffusion-Based Synthesis
Xinyu Hou, Zongsheng Yue, Xiaoming Li +1
In this work, we show that we only need a single parameter to effectively control granularity in diffusion-based synthesis. This parameter is incorporated during the denoising…