Varun Jampani

89

Papers

863

Total Citations

Papers (89)

SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusion

Probing the 3D Awareness of Visual Foundation Models

Stable Virtual Camera: Generative View Synthesis with Diffusion Models

SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglement

DiffusionLight: Light Probes for Free by Painting a Chrome Ball

ZeroShape: Regression-based Zero-shot Shape Reconstruction

SMooDi: Stylized Motion Diffusion Model

MVD-Fusion: Single-view 3D via Depth-consistent Multi-view Generation

Alchemist: Parametric Control of Material Properties with Diffusion Models

ZeST: Zero-Shot Material Transfer from a Single Image

WordRobe: Text-Guided Generation of Textured 3D Garments

SHINOBI: Shape and Illumination using Neural Object Decomposition via BRDF Optimization In-the-wild

ConDense: Consistent 2D-3D Pre-training for Dense and Sparse Features from Multi-View Images

PhysRig: Differentiable Physics-Based Skinning and Rigging Framework for Realistic Articulated Object Modeling

MARBLE: Material Recomposition and Blending in CLIP-Space

Stable Part Diffusion 4D: Multi-View RGB and Kinematic Parts Video Generation

NeurIPS 2025arXiv

SyncNoise: Geometrically Consistent Noise Prediction for Instruction-based 3D Editing

FaceCraft4D: Animated 3D Facial Avatar Generation from a Single Image

Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation

SCOPS: Self-Supervised Co-Part Segmentation

Pixel-Adaptive Convolutional Neural Networks

Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation

Self-Supervised Viewpoint Learning From Image Collections

From Image Collections to Point Clouds With Self-Supervised Shape and Pose Networks

Two-Shot Spatially-Varying BRDF and Shape Estimation

Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image Synthesis

LASR: Learning Articulated Shape Reconstruction From a Monocular Video

Adaptive Prototype Learning and Allocation for Few-Shot Segmentation

Decoupled Dynamic Filter Networks

AutoFlow: Learning a Better Training Set for Optical Flow

Learning ABCs: Approximate Bijective Correspondence for Isolating Factors of Variation With Weak Supervision

Uncertainty-Aware Adaptation for Self-Supervised 3D Human Pose Estimation

SOMSI: Spherical Novel View Synthesis With Soft Occlusion Multi-Sphere Images

NoisyTwins: Class-Consistent and Diverse Image Generation Through StyleGANs

MetaCLUE: Towards Comprehensive Visual Metaphors Research

LOCATE: Localize and Transfer Object Parts for Weakly Supervised Affordance Grounding

DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation

ShapeClipper: Scalable 3D Shape Learning From Single-View Images via Geometric and CLIP-Based Consistency

Semantic Video CNNs Through Representation Warping

Learning Propagation for Arbitrarily-Structured Data

SENSE: A Shared Encoder Network for Scene-Flow Estimation

Gated-SCNN: Gated Shape CNNs for Semantic Segmentation

Generalize Then Adapt: Source-Free Domain Adaptive Semantic Segmentation

Discovering 3D Parts From Image Collections

NeRD: Neural Reflectance Decomposition From Image Collections

SLIDE: Single Image 3D Photography With Soft Layering and Depth-Aware Inpainting

Infinite Nature: Perpetual View Generation of Natural Scenes From a Single Image

DreamBooth3D: Subject-Driven Text-to-3D Generation

ASIC: Aligning Sparse in-the-wild Image Collections

LU-NeRF: Scene and Pose Estimation by Synchronizing Local Unposed NeRFs

Appearance Consensus Driven Self-Supervised Human Mesh Recovery

DeepGMR: Learning Latent Gaussian Mixture Models for Registration

Self-supervised Single-view 3D Reconstruction via Semantic Consistency

Planes vs. Chairs: Category-Guided 3D Shape Learning without Any 3D Cues

Improving GANs for Long-Tailed Data through Group Spectral Regularization

Hierarchical Semantic Regularization of Latent Spaces in StyleGANs

Concurrent Subsidiary Supervision for Unsupervised Source-Free Domain Adaptation

Hi-LASSIE: High-Fidelity Articulated Shape and Skeleton Discovery From Sparse Image Ensemble

CompGS: Unleashing 2D Compositionality for Compositional Text-to-3D via Dynamically Optimizing 3D Gaussians

Unified Dense Prediction of Video Diffusion

SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Images

Not all Views are Created Equal: Analyzing Viewpoint Instabilities in Vision Foundation Models

SV4D 2.0: Enhancing Spatio-Temporal Consistency in Multi-View Video Diffusion for High-Quality 4D Generation

SViM3D: Stable Video Material Diffusion for Single Image 3D Generation

HouseCrafter: Lifting Floorplans to 3D Scenes with 2D Diffusion Models

Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence

One-Shot Open Affordance Learning with Foundation Models

HyperDreamBooth: HyperNetworks for Fast Personalization of Text-to-Image Models

NeRFiller: Completing Scenes via Generative 3D Inpainting

UniGS: Unified Representation for Image Generation and Segmentation

Optical Flow With Semantic Segmentation and Localized Layers

Learning Sparse High Dimensional Filters: Image Filtering, Dense CRFs and Bilateral Neural Networks

Video Propagation Networks

Learning Superpixels With Segmentation-Aware Affinity Loss

SPLATNet: Sparse Lattice Networks for Point Cloud Processing

Generative View Synthesis: From Single-view Semantics to Novel-view Images

Non-local Latent Relation Distillation for Self-Adaptive 3D Human Pose Estimation

Aligning Silhouette Topology for Self-Adaptive 3D Human Pose Recovery

Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decomposition

Robust Visual Reasoning via Language Guided Neural Module Networks

ViSER: Video-Specific Surface Embeddings for Articulated 3D Shape Reconstruction

Polynomial Neural Fields for Subband Decomposition and Manipulation

LASSIE: Learning Articulated Shapes from Sparse Image Ensemble via 3D Part Discovery

SAMURAI: Shape And Material from Unconstrained Real-world Arbitrary Image collections

Subsidiary Prototype Alignment for Universal Domain Adaptation

LayoutGPT: Compositional Visual Planning and Generation with Large Language Models

A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence

ARTIC3D: Learning Robust Articulated 3D Shapes from Noisy Web Image Collections

NAVI: Category-Agnostic Image Collections with High-Quality 3D Shape and Pose Annotations