papers

Publications (181)

cs.CV2023

3D-aware Conditional Image Synthesis

Kangle Deng, Gengshan Yang, Deva Ramanan +1

We propose pix2pix3D, a 3D-aware conditional generative model for controllable photorealistic image synthesis. Given a 2D label map, such as a segmentation or edge map, our model l…

cs.CV2017

Finding Tiny Faces

Peiyun Hu, Deva Ramanan

Though tremendous strides have been made in object recognition, one of the remaining open challenges is detecting small objects. We explore three aspects of the problem in the cont…

cs.CV2026

Modality Forcing for Scalable Spatial Generation

Bardienus Pieter Duisterhof, Deva Ramanan, Jeffrey Ichnowski +2

Text-to-image (T2I) models contain rich spatial priors. Synthesizing photorealistic, cluttered scenes requires an understanding of geometry, including perspective and relative scal…

cs.CV2026

MonoFusion: Sparse-View 4D Reconstruction via Monocular Fusion

Zihan Wang, Jeff Tan, Tarasha Khurana +2

We address the problem of dynamic scene reconstruction from sparse-view videos. Prior work often requires dense multi-view captures with hundreds of calibrated cameras (e.g. Panopt…

cs.HC2024

Evaluating a VR System for Collecting Safety-Critical Vehicle-Pedestrian Interactions

Erica Weng, Kenta Mukoya, Deva Ramanan +1

Autonomous vehicles (AVs) require comprehensive and reliable pedestrian trajectory data to ensure safe operation. However, obtaining data of safety-critical scenarios such as jaywa…

cs.LG2020

What-If Motion Prediction for Autonomous Driving

Siddhesh Khandelwal, William Qi, Jagjeet Singh +2

Forecasting the long-term future motion of road actors is a core challenge to the deployment of safe autonomous vehicles (AVs). Viable solutions must account for both the static ge…