Niloy J. Mitra

papers

1,659

total citations

papers (27)

Pix2Video: Video Editing using Image Diffusion

ICCV 2023arXiv

344

citations

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

CVPR 2023arXiv

203

citations

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

CVPR 2024arXiv

citations

StructEdit: Learning Structural Shape Variations

CVPR 2020arXiv

citations

Learning Delaunay Surface Elements for Mesh Reconstruction

CVPR 2021arXiv

citations

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

ICCV 2021arXiv

citations

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

CVPR 2024arXiv

citations

HoloFusion: Towards Photo-realistic 3D Generative Modeling

ICCV 2023arXiv

citations

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

CVPR 2025arXiv

citations

Neural Surface Maps

CVPR 2021arXiv

citations

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

CVPR 2023arXiv

citations

Glass: Geometric Latent Augmentation for Shape Spaces

CVPR 2022arXiv

citations

SuperGaussian: Repurposing Video Models for 3D Super Resolution

ECCV 2024arXiv

citations

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

CVPR 2024arXiv

citations

Neural Convolutional Surfaces

CVPR 2022arXiv

citations

Going Deeper With Lean Point Networks

CVPR 2020arXiv

citations

Motion Modes: What Could Happen Next?

CVPR 2025arXiv

citations

From Programs to Poses: Factored Real-World Scene Generation via Learned Program Libraries

NEURIPS 2025arXiv

citations

LIM: Large Interpolator Model for Dynamic Reconstruction

CVPR 2025arXiv

citations

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

CVPR 2021

citations

Points2Surf Learning Implicit Surfaces from Point Clouds

ECCV 2020

citations

Niloy J. Mitra

papers (27)

Pix2Video: Video Editing using Image Diffusion

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

ShapeFormer: Transformer-Based Shape Completion via Sparse Representation

Im2Vec: Synthesizing Vector Graphics Without Vector Supervision

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

Learning a Neural 3D Texture Space From 2D Exemplars

Labels4Free: Unsupervised Segmentation Using StyleGAN

InsetGAN for Full-Body Image Generation

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

StructEdit: Learning Structural Shape Variations

Learning Delaunay Surface Elements for Mesh Reconstruction

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

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

HoloFusion: Towards Photo-realistic 3D Generative Modeling

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

Neural Surface Maps

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

Glass: Geometric Latent Augmentation for Shape Spaces

SuperGaussian: Repurposing Video Models for 3D Super Resolution

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

Neural Convolutional Surfaces

Going Deeper With Lean Point Networks

Motion Modes: What Could Happen Next?

From Programs to Poses: Factored Real-World Scene Generation via Learned Program Libraries

LIM: Large Interpolator Model for Dynamic Reconstruction

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

Points2Surf Learning Implicit Surfaces from Point Clouds

papers (27)

Pix2Video: Video Editing using Image Diffusion

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

ShapeFormer: Transformer-Based Shape Completion via Sparse Representation

Im2Vec: Synthesizing Vector Graphics Without Vector Supervision

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

Learning a Neural 3D Texture Space From 2D Exemplars

Labels4Free: Unsupervised Segmentation Using StyleGAN

InsetGAN for Full-Body Image Generation

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

StructEdit: Learning Structural Shape Variations

Learning Delaunay Surface Elements for Mesh Reconstruction

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

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

HoloFusion: Towards Photo-realistic 3D Generative Modeling

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

Neural Surface Maps

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

Glass: Geometric Latent Augmentation for Shape Spaces

SuperGaussian: Repurposing Video Models for 3D Super Resolution

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

Neural Convolutional Surfaces

Going Deeper With Lean Point Networks

Motion Modes: What Could Happen Next?

From Programs to Poses: Factored Real-World Scene Generation via Learned Program Libraries

LIM: Large Interpolator Model for Dynamic Reconstruction

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

Points2Surf Learning Implicit Surfaces from Point Clouds