Search papers, labs, and topics across Lattice.
The Hong Kong Polytechnic University, Visual Computing Lab, OPPO Research Institute
3
0
4
TV-Edit achieves unprecedented precision in image editing by merging the semantic richness of text with the spatial accuracy of visual prompts.
Unified benchmarks reveal the state-of-the-art in simultaneously addressing multiple real-world image degradations like blur, low-light, and rain.
Achieve content-consistent image edits without sacrificing quality by using region-regularized reinforcement learning that preserves unedited regions.
