2 citations · 6 across the 32 of their papers we have counts for
27 papers · 1 filter
RefRoute: Decoupling Conditioning Cost from References via Compact Residual Conditioning and Spatial Routing
Wanning He, Yuyao Zhang, Yu-Wing Tai
Multi-reference image generation requires preserving the appearance of multiple subjects while composing them into a coherent scene. However, existing diffusion transformers common…
Just Align : Aligning Predictions, Not Representations
Yuyao Zhang, Yuwei Hu, Ziyang Mai +1
Representation alignment has become an effective way to accelerate diffusion training, but its benefits do not transfer reliably to pixel-space clean-image prediction. In JiT, we f…
When Latents Forget Pixels: Restoring Fidelity in Diffusion Transformer Super-Resolution
Yu Shi, Yuyao Zhang, Yu-wing Tai
Image super-resolution (SR) with large generative models has recently achieved remarkable perceptual quality, yet maintaining fidelity to the LR observation remains challenging. In…
IDEAL-Bench: Indoor Dataset and Evaluation suite for Analyzing 3D Layout reasoning
Yuening Cai, Junwei Zhou, Youran Qu +1
Spatial question answering is the dominant paradigm for evaluating spatial intelligence in Vision-Language Models (VLMs), but it leaves a complementary axis of spatial competence u…
Beyond MoCap: Scaling Motion Tokenizers with Synthetic Human Motion for Generative Modeling
Yiwen Yan, Wanning He, Yu-Wing Tai
Human motion generation models are fundamentally constrained by the limited diversity of motion capture datasets, which predominantly contain common, repetitive actions and fail to…
HierEdit: Region-Aware Hierarchical Diffusion for Efficient High-Resolution Editing
Yuyao Zhang, Alexander Huang-Menders, Yu-Wing Tai
High-resolution image editing is essential for professional and creative applications, yet existing multimodal diffusion-based editors remain computationally inefficient and constr…
AtlasVid: Efficient Ultra-High-Resolution Long Video Generation via Decoupled Global-Local Modeling
Ziyang Mai, Yuyao Zhang, Yu-Wing Tai
Recent diffusion-based video generators have achieved remarkable visual fidelity and prompt controllability, yet scaling them to ultra-high-resolution (UHR) long videos remains pro…
CoT-Seg: Rethinking Segmentation with Chain-of-Thought Reasoning and Self-Correction
Shiu-hong Kao, Chak Ho Huang, Huaiqian Liu +2
Existing works of reasoning segmentation often fall short in complex cases, particularly when addressing complicated queries and out-of-domain images. Inspired by the chain-of-thou…
Trace Anything: Representing Any Video in 4D via Trajectory Fields
Xinhang Liu, Yuxi Xiao, Donny Y. Chen +4
Effective spatio-temporal representation is fundamental to modeling, understanding, and predicting dynamics in videos. The atomic unit of a video, the pixel, traces a continuous 3D…
SmartAvatar: Text- and Image-Guided Human Avatar Generation with VLM AI Agents
Alexander Huang-Menders, Xinhang Liu, Andy Xu +3
SmartAvatar is a vision-language-agent-driven framework for generating fully rigged, animation-ready 3D human avatars from a single photo or textual prompt. While diffusion-based m…
Agentic 3D Scene Generation with Spatially Contextualized VLMs
Xinhang Liu, Yu-Wing Tai, Chi-Keung Tang
Despite recent advances in multimodal content generation enabled by vision-language models (VLMs), their ability to reason about and generate structured 3D scenes remains largely u…
CoT-RVS: Zero-Shot Chain-of-Thought Reasoning Segmentation for Videos
Shiu-hong Kao, Yu-Wing Tai, Chi-Keung Tang
Reasoning Video Object Segmentation is a challenging task, aiming at generating a mask sequence from an input video given a complex and implicit text query. While existing works fi…
Multimodal Generation of Animatable 3D Human Models with AvatarForge
Xinhang Liu, Yu-Wing Tai, Chi-Keung Tang
We introduce AvatarForge, a framework for generating animatable 3D human avatars from text or image inputs using AI-driven procedural generation. While diffusion-based methods have…
Think Before You Segment: High-Quality Reasoning Segmentation with GPT Chain of Thoughts
Shiu-hong Kao, Yu-Wing Tai, Chi-Keung Tang
Reasoning segmentation is a challenging vision-language task that aims to output the segmentation mask with respect to a complex, implicit, and even non-visual query text. Previous…
WorldCraft: Photo-Realistic 3D World Creation and Customization via LLM Agents
Xinhang Liu, Chi-Keung Tang, Yu-Wing Tai
Constructing photorealistic virtual worlds has applications across various fields, but it often requires the extensive labor of highly trained professionals to operate conventional…
UVRM: A Scalable 3D Reconstruction Model from Unposed Videos
Shiu-hong Kao, Xiao Li, Jinglu Wang +4
Large Reconstruction Models (LRMs) have recently become a popular method for creating 3D foundational models. Training 3D reconstruction models with 2D visual data traditionally re…
ChatCam: Empowering Camera Control through Conversational AI
Xinhang Liu, Yu-Wing Tai, Chi-Keung Tang
Cinematographers adeptly capture the essence of the world, crafting compelling visual narratives through intricate camera movements. Witnessing the strides made by large language m…
VP-LLM: Text-Driven 3D Volume Completion with Large Language Models through Patchification
Jianmeng Liu, Yichen Liu, Yuyao Zhang +3
Recent conditional 3D completion works have mainly relied on CLIP or BERT to encode textual information, which cannot support complex instruction. Meanwhile, large language models…
Gear-NeRF: Free-Viewpoint Rendering and Tracking with Motion-aware Spatio-Temporal Sampling
Xinhang Liu, Yu-Wing Tai, Chi-Keung Tang +3
Extensions of Neural Radiance Fields (NeRFs) to model dynamic scenes have enabled their near photo-realistic, free-viewpoint rendering. Although these methods have shown some poten…
Motion-Agent: A Conversational Framework for Human Motion Generation with LLMs
Qi Wu, Yubo Zhao, Yifan Wang +3
While previous approaches to 3D human motion generation have achieved notable success, they often rely on extensive training and are limited to specific tasks. To address these cha…
FED-NeRF: Achieve High 3D Consistency and Temporal Coherence for Face Video Editing on Dynamic NeRF
Hao Zhang, Yu-Wing Tai, Chi-Keung Tang
The success of the GAN-NeRF structure has enabled face editing on NeRF to maintain 3D view consistency. However, achieving simultaneously multi-view consistency and temporal cohere…
Inpaint4DNeRF: Promptable Spatio-Temporal NeRF Inpainting with Generative Diffusion Models
Han Jiang, Haosen Sun, Ruoxuan Li +2
Current Neural Radiance Fields (NeRF) can generate photorealistic novel views. For editing 3D scenes represented by NeRF, with the advent of generative models, this paper proposes…
Prompt2NeRF-PIL: Fast NeRF Generation via Pretrained Implicit Latent
Jianmeng Liu, Yuyao Zhang, Zeyuan Meng +2
This paper explores promptable NeRF generation (e.g., text prompt or single image prompt) for direct conditioning and fast generation of NeRF parameters for the underlying 3D scene…
Stable Segment Anything Model
Qi Fan, Xin Tao, Lei Ke +6
The Segment Anything Model (SAM) achieves remarkable promptable segmentation given high-quality prompts which, however, often require good skills to specify. To make SAM robust to…