Niloy J. Mitra

30 papers · 2019–2025 · 4 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (15) 🌍 Conference Polyglot (4) 🏃 Academic Marathon (6) 🌈 Renaissance Researcher (7) 🌉 Interdisciplinary Bridge 🗺️ Taxonomy Completionist (45) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🏠 Conference Loyalist (20) 🔬 Deep Specialist (12) 💎 Century Club (30) ⚡ Prolific Year (5) ❓ The Questioner 🔥 Unstoppable (7) 🗃️ Keyword Collector (149)

Conferences

CVPR (20) ICCV (6) ECCV (3) ICLR (1)

Top co-authors

Paul Guerrero (8) Duygu Ceylan (5) David Novotny (4) Noam Aigerman (4) Andrea Vedaldi (3) Animesh Karnewar (3) Chun-Hao P. Huang (3) Peter Wonka (3) Vladimir G. Kim (3) Karran Pandey (2)

Research topics

Digital Humanities (1)

Keywords

diffusion model (8) point cloud (5) 3d generation (4) 3d shape (4) image generation (4) 3d reconstruction (4) video generation (3) 3d vision (3) neural rendering (3) generative model (3) neural network (3) differentiable rendering (2) geometry processing (2) variational autoencoder (2) latent space (2) semantic segmentation (2) depth estimation (2) pose estimation (2) image synthesis (2) generative adversarial network (2)

Papers

Motion Modes: What Could Happen Next? CVPR 2025

Track4Gen: Teaching Video Diffusion Models to Track Points Improves Video Generation CVPR 2025

LIM: Large Interpolator Model for Dynamic Reconstruction CVPR 2025

SuperGaussian: Repurposing Video Models for 3D Super Resolution ECCV 2024

Diffusion Handles Enabling 3D Edits for Diffusion Models by Lifting Activations to 3D CVPR 2024

CADTalk: An Algorithm and Benchmark for Semantic Commenting of CAD Programs CVPR 2024

Diffusion 3D Features (Diff3F): Decorating Untextured Shapes with Distilled Semantic Features CVPR 2024

GOEmbed: Gradient Origin Embeddings for Representation Agnostic 3D Feature Learning ECCV 2024

HOLODIFFUSION: Training a 3D Diffusion Model Using 2D Images CVPR 2023

HoloFusion: Towards Photo-realistic 3D Generative Modeling ICCV 2023

Pix2Video: Video Editing using Image Diffusion ICCV 2023

RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation CVPR 2023

Blowing in the Wind: CycleNet for Human Cinemagraphs From Still Images CVPR 2023

Glass: Geometric Latent Augmentation for Shape Spaces CVPR 2022

InsetGAN for Full-Body Image Generation CVPR 2022

Neural Convolutional Surfaces CVPR 2022

ShapeFormer: Transformer-Based Shape Completion via Sparse Representation CVPR 2022

Im2Vec: Synthesizing Vector Graphics Without Vector Supervision CVPR 2021

Labels4Free: Unsupervised Segmentation Using StyleGAN ICCV 2021

CPFN: Cascaded Primitive Fitting Networks for High-Resolution Point Clouds ICCV 2021

Seeing Behind Objects for 3D Multi-Object Tracking in RGB-D Sequences CVPR 2021

Neural Surface Maps CVPR 2021

Learning Delaunay Surface Elements for Mesh Reconstruction CVPR 2021

Unpaired Point Cloud Completion on Real Scans using Adversarial Training ICLR 2020

Going Deeper With Lean Point Networks CVPR 2020

Learning a Neural 3D Texture Space From 2D Exemplars CVPR 2020

Points2Surf Learning Implicit Surfaces from Point Clouds ECCV 2020

StructEdit: Learning Structural Shape Variations CVPR 2020

Neural Re-Simulation for Generating Bounces in Single Images ICCV 2019

Escaping Plato's Cave: 3D Shape From Adversarial Rendering ICCV 2019