TencentARC

GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

PhotoMaker [CVPR 2024]

InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models

T2I-Adapter

[SIGGRAPH 2026] Pixal3D: Pixel-Aligned 3D Generation from Images

[ECCV 2024] The official implementation of paper "BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion"

Official Code for MotionCtrl [SIGGRAPH 2024]

SEED-Voken: A Series of Powerful Visual Tokenizers

SEED-Story: Multimodal Long Story Generation with Large Language Model

[ICCV 2023] Consistent Image Synthesis and Editing

[SIGGRAPH2025] Official repo for paper "Any-length Video Inpainting and Editing with Plug-and-Play Context Control"

The official repo of GameHorizon, a unified data and evaluation suite that measures AAA gameplay capabilities at different temporal horizons for diverse model families.

[ICLR 2026] Streamlining Cartoon Production with Generative Post-Keyframing

[TPAMI] The official implementation of paper "BrushEdit: All-In-One Image Inpainting and Editing"

[Arxiv 2026] WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory

[arxiv'26] GAE: Learning a Geometry-Native Latent Space for 3D-Consistent World Generation

A framework to convert any 2D videos to immersive stereoscopic 3D

[ACL 2024] Progressive LLaMA with Block Expansion.

The official implementation of paper "ColorFlow: Retrieval-Augmented Image Sequence Colorization". ColorFlow：基于检索增强的图像序列上色

[ICLR 2026] Official Repo for Rolling Forcing: Autoregressive Long Video Diffusion in Real Time

[ICCV 2025] GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors

VerseCrafter: Dynamic Realistic Video World Model with 4D Geometric Control

NeurIPS 2023, Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models

Codes for "AnimeSR: Learning Real-World Super-Resolution Models for Animation Videos"

Official code of SmartEdit [CVPR-2024 Highlight]

ECCV 2022, Oral, VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder

[ICCV 2025] AnimeGamer: Infinite Anime Life Simulation with Next Game State Prediction

[ECCV 2026] Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels

[CVPR 2025] Official code of "DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation"

AudioStory: Generating Long-Form Narrative Audio with Large Language Models

Looking Ahead: Modeling Future Evolution in Autoregressive Video Generation

[ICCV 2025] FreeSplatter: Pose-free Gaussian Splatting for Sparse-view 3D Reconstruction

Structured Video Comprehension of Real-World Shorts

UMT is a unified and flexible framework which can handle different input modality combinations, and output video moment retrieval and/or highlight detection results.

[IJCV🎉] TokLIP: Marry Visual Tokens to CLIP for Multimodal Comprehension and Generation

SCoPE: Sightline-Coordinate Positional Encoding for 3D-Aware Video Generation

Player-1: Learning to Play from Synthetic Experience

[CVPR 2026 Highlight🔥] MotionCrafter: Dense Geometry and Motion Reconstruction with a 4D VAE

[CVPR 2024] ViT-Lens: Towards Omni-modal Representations

[CVPR 2026] TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs

[ICCV2025 Oral] Latent Motion Token as the Bridging Language for Learning Robot Manipulation from Videos

Codes for "Metric Learning based Interactive Modulation for Real-World Super-Resolution"

[ICLR'26] IC-Custom: Diverse Image Customization via In-Context Learning

[ECCV 2024🔥] Official implementation of the paper "ST-LLM: Large Language Models Are Effective Temporal Learners"

[ICLR 2026] GenCompositor: Generative Video Compositing with Diffusion Transformer

Official codes for DeSRA (ICML 2023)

Code release of our paper "DI-PCG: Diffusion-based Efficient Inverse Procedural Content Generation for High-quality 3D Asset Creation".

Official code for "Bridging Video-text Retrieval with Multiple Choice Questions", CVPR 2022 (Oral).

[NeurIPS2025] The official implementation of MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO

[CVPR 2026] Spatio-Temporal Autoregressive 4K 360° Video Generation from Perspective Video

[CVPR 2025] Boosting Generative Novel View Synthesis with Sparse and Unposed Images

NeurIPS 2021, Spotlight, Finding Discriminative Filters for Specific Degradations in Blind Super-Resolution

Nerf and extensions in all

Multics: Generative Multi-Player World Model with Hierarchical Communication

[ECCV 2026] Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?

mllm-npu: training multimodal large language models on Ascend NPUs

Diffusion Powers Video Tokenizer for Comprehension and Generation (CVPR 2025)

[ACL2026 Findings] GRPO-CARE: Consistency-Aware Reinforcement Learning for Multimodal Reasoning

SurfelNeRF: Neural Surfel Radiance Fields for Online Photorealistic Reconstruction of Indoor Scenes

Codes for "RepSR: Training Efficient VGG-style Super-Resolution Networks with Structural Re-Parameterization and Batch Normalization"

HOSNeRF: Dynamic Human-Object-Scene Neural Radiance Fields from a Single Video

Codes for "Mitigating Artifacts in Real-World Video Super-Resolution Models"

Official code for "What Makes for Good Visual Tokenizers for Large Language Models?".

Official codes for ConMIM (ICLR 2023)