Philip Torr

8

Papers

150

Total Citations

Papers (8)

Stable Virtual Camera: Generative View Synthesis with Diffusion Models

Real-Fake: Effective Training Data Synthesis Through Distribution Matching

VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory

PoisonBench: Assessing Language Model Vulnerability to Poisoned Preference Data

Towards Reliable Identification of Diffusion-based Image Manipulations

6402 NeRF-VPT: Learning Novel View Representations with Neural Radiance Fields via View Prompt Tuning

SafetyDPO: Scalable Safety Alignment for Text-to-Image Generation

MatchDiffusion: Training-free Generation of Match-Cuts