Peter Vajda

papers

2,349

total citations

papers (21)

Open-Vocabulary Semantic Segmentation With Mask-Adapted CLIP

CVPR 2023arXiv

630

citations

SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation

ECCV 2020arXiv

413

citations

FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions

CVPR 2020arXiv

321

citations

NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detection

ICCV 2023arXiv

citations

Image2Point: 3D Point-Cloud Understanding with 2D Image Pretrained Models

ECCV 2022arXiv

citations

ControlRoom3D: Room Generation using Semantic Proxy Rooms

CVPR 2024arXiv

citations

Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference

CVPR 2023arXiv

citations

Fairy: Fast Parallelized Instruction-Guided Video-to-Video Synthesis

CVPR 2024arXiv

citations

Open-Set Semi-Supervised Object Detection

ECCV 2022arXiv

citations

LinGen: Towards High-Resolution Minute-Length Text-to-Video Generation with Linear Computational Complexity

CVPR 2025arXiv

citations

Deep Space-Time Video Upsampling Networks

ECCV 2020arXiv

citations

Movie Weaver: Tuning-Free Multi-Concept Video Personalization with Anchored Prompts

CVPR 2025arXiv

citations

A Practical Stereo Depth System for Smart Glasses

CVPR 2023arXiv

citations

Geometric Correspondence Fields: Learned Differentiable Rendering for 3D Pose Refinement in the Wild

ECCV 2020arXiv

citations

Tackling the Ill-Posedness of Super-Resolution Through Adaptive Target Generation

CVPR 2021

citations

Visual Transformers: Where Do Transformers Really Belong in Vision Models?

ICCV 2021

citations

Peter Vajda

papers (21)

Open-Vocabulary Semantic Segmentation With Mask-Adapted CLIP

SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation

FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions

Cross-Domain Adaptive Teacher for Object Detection

Cache Me if You Can: Accelerating Diffusion Models through Block Caching

FBNetV3: Joint Architecture-Recipe Search Using Predictor Pretraining

AVID: Any-Length Video Inpainting with Diffusion Model

FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis

NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detection

Image2Point: 3D Point-Cloud Understanding with 2D Image Pretrained Models

ControlRoom3D: Room Generation using Semantic Proxy Rooms

Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference

Fairy: Fast Parallelized Instruction-Guided Video-to-Video Synthesis

Open-Set Semi-Supervised Object Detection

LinGen: Towards High-Resolution Minute-Length Text-to-Video Generation with Linear Computational Complexity

Deep Space-Time Video Upsampling Networks

Movie Weaver: Tuning-Free Multi-Concept Video Personalization with Anchored Prompts

A Practical Stereo Depth System for Smart Glasses

Geometric Correspondence Fields: Learned Differentiable Rendering for 3D Pose Refinement in the Wild

Tackling the Ill-Posedness of Super-Resolution Through Adaptive Target Generation

Visual Transformers: Where Do Transformers Really Belong in Vision Models?

papers (21)

Open-Vocabulary Semantic Segmentation With Mask-Adapted CLIP

SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation

FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions

Cross-Domain Adaptive Teacher for Object Detection

Cache Me if You Can: Accelerating Diffusion Models through Block Caching

FBNetV3: Joint Architecture-Recipe Search Using Predictor Pretraining

AVID: Any-Length Video Inpainting with Diffusion Model

FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis

NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detection

Image2Point: 3D Point-Cloud Understanding with 2D Image Pretrained Models

ControlRoom3D: Room Generation using Semantic Proxy Rooms

Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference

Fairy: Fast Parallelized Instruction-Guided Video-to-Video Synthesis

Open-Set Semi-Supervised Object Detection

LinGen: Towards High-Resolution Minute-Length Text-to-Video Generation with Linear Computational Complexity

Deep Space-Time Video Upsampling Networks

Movie Weaver: Tuning-Free Multi-Concept Video Personalization with Anchored Prompts

A Practical Stereo Depth System for Smart Glasses

Geometric Correspondence Fields: Learned Differentiable Rendering for 3D Pose Refinement in the Wild

Tackling the Ill-Posedness of Super-Resolution Through Adaptive Target Generation

Visual Transformers: Where Do Transformers Really Belong in Vision Models?