Deva Ramanan

18

Papers

527

Total Citations

Papers (18)

SplaTAM: Splat Track & Map 3D Gaussians for Dense RGB-D SLAM

AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesis

ZeroFlow: Scalable Scene Flow via Distillation

Generating Physically Stable and Buildable Brick Structures from Text

Neural Eulerian Scene Flow Fields

MonoFusion: Sparse-View 4D Reconstruction via Monocular Fusion

Enhancing Few-Shot Vision-Language Classification with Large Multimodal Model Features

Efficient Autoregressive Shape Generation via Octree-Based Adaptive Tokenization

Reconstruct, Inpaint, Test-Time Finetune: Dynamic Novel-view Synthesis from Monocular Videos

NeurIPS 2025arXiv

Towards Foundational Models for Single-Chip Radar

Using Diffusion Priors for Video Amodal Segmentation

Reanimating Images using Neural Representations of Dynamic Stimuli

DiffusionSfM: Predicting Structure and Motion via Ray Origin and Endpoint Diffusion

ONLY: One-Layer Intervention Sufficiently Mitigates Hallucinations in Large Vision-Language Models

HybridNeRF: Efficient Neural Rendering via Adaptive Volumetric Surfaces

Language Models as Black-Box Optimizers for Vision-Language Models

The Neglected Tails in Vision-Language Models

Revisiting the Role of Language Priors in Vision-Language Models