Princeton Vision & Learning Lab (@PrincetonVL) / X

Princeton Vision & Learning Lab

56 posts

Princeton Vision & Learning Lab

@PrincetonVL

pvl.cs.princeton.edu

Princeton, NJ

Joined March 2023

Princeton Vision & Learning Lab
@PrincetonVL
Jul 8
We've released a preview of Infinigen 2.0 - new high quality procedural materials and scenes with an efficient and controllable Python API. See below for info!
Alexander Raistrick
@alex_raistrick
Jul 8
1/ We've released Infinigen 2.0! Currently in preview. It creates indoor 3D scene files in 1min CPU time, and includes new and better materials --- all still fully procedural. Our new 2.0 design is highly efficient and allows easy control and recombination via Python APIs.
00:00
Princeton Vision & Learning Lab
@PrincetonVL
Mar 31
Stereo depth is highly useful for robots. Meet WAFT-Stereo: #1 on ETH3D (BP-0.5), Middlebury (RMSE), and KITTI (all metrics); 61% less zero-shot ETH3D BP-0.5 error; 1.8-6.7x faster than prior SOTA. Key idea: classify disparity into bins, then iterative high-res warping.🧵1/2
00:00
Princeton Vision & Learning Lab
@PrincetonVL
Feb 10
Meet WAFT (Warping-Alone Field Transforms), our new optical-flow estimator. #1 on public benchmarks (Sintel & Spring), 1.3-4.1x faster than leading methods, and 2x lower memory. Key idea: replace cost volumes with high-res feature-space warping. Code and paper:👇
00:00
Princeton Vision & Learning Lab
@PrincetonVL
Dec 1, 2025
Estimating camera intrinsics from video is key to 3D reconstruction, but most methods assume they’re fixed per video. What if the camera keeps zooming and refocusing? Meet InFlux, the first benchmark with per-frame ground truth for videos with dynamic intrinsics. 🧵1/5
00:00
Princeton Vision & Learning Lab
@PrincetonVL
Nov 17, 2025
Major update to Infinigen Articulated (formerly Infinigen-Sim)! You can now generate articulated 3D objects in 18 categories, simulation ready with physics parameters and improved efficiency. Also available: 20k pre-generated objects. Download links below👇
GIF