Search papers, labs, and topics across Lattice.
National Yang Ming Chiao Tung University
6
0
6
3
LongE2V achieves unprecedented temporal coherence in video reconstruction from sparse event data, outperforming all existing methods.
Achieving dual-semantic 3D visual illusions in mere minutes, JanusMesh outshines traditional methods in both speed and quality.
By merging physical modeling with generative priors, BRDFusion achieves unprecedented control and quality in urban scene rendering, setting a new standard for inverse rendering applications.
Reroute reveals that visual token importance is dynamic, allowing for improved grounding in VLMs without sacrificing performance through aggressive token reduction.
Benchmarking reveals that a diffusion-based 2D enhancer can significantly elevate the performance of distractor-free radiance field methods, achieving nearly 1 dB PSNR improvement.
Training generative inverse renderers on AAA game footage closes the realism gap, enabling superior generalization and controllable generation compared to models trained on existing synthetic datasets.
