Maneesh Agrawala

11 papers · 2021–2025 · 4 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (14) 🌍 Conference Polyglot (4) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🌈 Renaissance Researcher (7) 🌉 Interdisciplinary Bridge 🗺️ Taxonomy Completionist (26) 🔥 Unstoppable (5) 💎 Century Club (11)

Conferences

CVPR (4) ICCV (3) ECCV (2) ICLR (2)

Top co-authors

Anyi Rao (5) Ceyuan Yang (3) Dahua Lin (3) Yuwei Guo (3) Bo Dai (3) Ranjay Krishna (2) Tinghui Zhou (2) Jun-Yan Zhu (2) Lvmin Zhang (2) Kangle Deng (2)

Keywords

video question answering (2) compositional reasoning (2) video generation (1) 3d shape generation (1) self-supervised learning (1) question decomposition (1) image editing (1) visual reasoning (1) text-to-image generation (1) neural rendering (1) generative model (1) diffusion model (1) tree structure (1) autoregressive model (1) disentangled representation (1) variational autoencoder (1) neural radiance field (1) novel view synthesis (1) video editing (1) stable diffusion (1)

Papers

Keyframe-Guided Creative Video Inpainting CVPR 2025

Scaling In-the-Wild Training for Diffusion-based Illumination Harmonization and Editing by Imposing Consistent Light Transport ICLR 2025

Efficient Autoregressive Shape Generation via Octree-Based Adaptive Tokenization ICCV 2025

SparseCtrl: Adding Sparse Controls to Text-to-Video Diffusion Models ECCV 2024

FlashTex: Fast Relightable Mesh Texturing with LightControlNet ECCV 2024

AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning ICLR 2024

Tree-Structured Shading Decomposition ICCV 2023

Adding Conditional Control to Text-to-Image Diffusion Models ICCV 2023

Disentangled3D: Learning a 3D Generative Model With Disentangled Geometry and Appearance From Monocular Images CVPR 2022

Measuring Compositional Consistency for Video Question Answering CVPR 2022

AGQA: A Benchmark for Compositional Spatio-Temporal Reasoning CVPR 2021