Chunhua Shen
- Papers
- 51
Cite
Notes
Only stored in your browser.
Authored papers
51Geo-Align: Video Generation Alignment via Metric Geometry Reward
arXiv 2026
Exploring Spatial Intelligence from a Generative Perspective
arXiv 2026
TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders
arXiv 2026
MARBLE: Multi-Aspect Reward Balance for Diffusion RL
arXiv 2026
Beyond Hard Masks: Progressive Token Evolution for Diffusion Language Models
arXiv 2026
OmniJigsaw: Enhancing Omni-Modal Reasoning via Modality-Orchestrated Reordering
arXiv 2026
Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration
arXiv 2025
DICEPTION: A Generalist Diffusion Model for Visual Perceptual Tasks
arXiv 2025
SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories
arXiv 2025
ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learning
arXiv 2025
Revisiting Depth Representations for Feed-Forward 3D Gaussian Splatting
arXiv 2025
$π^3$: Scalable Permutation-Equivariant Visual Geometry Learning
arXiv 2025
Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language Models
arXiv 2025
Uniform Discrete Diffusion with Metric Path for Video Generation
arXiv 2025
OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling
arXiv 2025
Aether: Geometric-Aware Unified World Modeling
ICCV 2025
WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool
arXiv 2025
Tinker: Diffusion's Gift to 3D--Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimization
arXiv 2025
POMATO: Marrying Pointmap Matching with Temporal Motion for Dynamic 3D Reconstruction
ICCV 2025
MobileVLM V2: Faster and Stronger Baseline for Vision Language Model
arXiv 2024
What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?
arXiv 2024
Depth Any Video with Scalable Synthetic Data
arXiv 2024
Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation
metric3d-v2-a-versatile-monocular-geometric
VisionLLaMA: A Unified LLaMA Backbone for Vision Tasks
arXiv 2024
FreeCustom: Tuning-Free Customized Image Generation for Multi-Concept Composition
CVPR 2024 1
GeoBench: Benchmarking and Analyzing Monocular Geometry Estimation Models
arXiv 2024
DiverGen: Improving Instance Segmentation by Learning Wider Data Distribution with More Diverse Generative Data
CVPR 2024 1
Unleashing the Potential of the Diffusion Model in Few-shot Semantic Segmentation
arXiv 2024
FreeCompose: Generic Zero-Shot Image Composition with Diffusion Prior
arXiv 2024
PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm
arXiv 2023
CTVIS: Consistent Training for Online Video Instance Segmentation
ICCV 2023 1
SegGPT: Segmenting Everything In Context
arXiv 2023
Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching
arXiv 2023
DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models
ICCV 2023 1
Zero-Shot Video Editing Using Off-The-Shelf Image Diffusion Models
arXiv 2023
StableLLaVA: Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data
arXiv 2023
SegViTv2: Exploring Efficient and Continual Semantic Segmentation with Plain Vision Transformers
arXiv 2023
AutoStory: Generating Diverse Storytelling Images with Minimal Human Effort
arXiv 2023
SegPrompt: Boosting Open-world Segmentation via Category-level Prompt Learning
ICCV 2023 1
Zolly: Zoom Focal Length Correctly for Perspective-Distorted Human Mesh Reconstruction
ICCV 2023 1
Object-aware Inversion and Reassembly for Image Editing
arXiv 2023
LoRAPrune: Structured Pruning Meets Low-Rank Parameter-Efficient Fine-Tuning
arXiv 2023
Generative Prompt Model for Weakly Supervised Object Localization
ICCV 2023 1
StyleAvatar3D: Leveraging Image-Text Diffusion Models for High-Fidelity 3D Avatar Generation
arXiv 2023
FoPro: Few-Shot Guided Robust Webly-Supervised Prototypical Learning
arXiv 2022
Poseur: Direct Human Pose Regression with Transformers
arXiv 2022
Twins: Revisiting the Design of Spatial Attention in Vision Transformers
NeurIPS 2021 12
Conditional Positional Encodings for Vision Transformers
arXiv 2021
ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network
abcnet-real-time-scene-text-spotting-with-1
End-to-End Video Instance Segmentation with Transformers
CVPR 2021 1
FCOS: Fully Convolutional One-Stage Object Detection
fcos-fully-convolutional-one-stage-object-1
Affiliations
Frequent co-authors
10from 51 papers