| website | https://hermannblum.net |
It takes a while to make fancy #NeRF animations, so I am very happy we can now share our upcoming #CVPR paper with video and code release:
A big debate in #ContinualLearning is how to scale to many experiences. This work shows how well NeRF-based compression can scale to store robotic experiences over many consecutive deployments, much better than storing checkpoints of your model.
website: https://ethz-asl.github.io/ucsa_neural_rendering/
#Robotics #SceneUnderstanding
Statement from the listed authors of Stochastic Parrots on the “AI pause” letter
https://www.dair-institute.org/blog/letter-statement-March2023
"Regulatory efforts should focus on transparency, accountability and preventing exploitative labor practices."
With @timnitGebru @meg and Angelina McMillan-Major
Just obtained a PDF of the article that (as far as I know) for the first time in the scientific literature uses the phrase "Publish or perish". It is from 1927 - but if you'd publish it again in 2027, I think no one would notice 😀
Case, C. M. (1927). Scholarship in sociology. Sociology and Social Research, 12, 323–340.
NICER-SLAM: Neural Implicit Scene Encoding for RGB SLAM
Zihan Zhu, Songyou Peng, Viktor Larsson, Zhaopeng Cui, Martin R. Oswald, Andreas Geiger, Marc Pollefeys
tl;dr: from RGBD to RGB input: add monodepth, mononormals and optical flow + hierarchical grid
Neural implicit representations have recently become popular in simultaneous localization and mapping (SLAM), especially in dense visual SLAM. However, previous works in this direction either rely on RGB-D sensors, or require a separate monocular SLAM approach for camera tracking and do not produce high-fidelity dense 3D scene reconstruction. In this paper, we present NICER-SLAM, a dense RGB SLAM system that simultaneously optimizes for camera poses and a hierarchical neural implicit map representation, which also allows for high-quality novel view synthesis. To facilitate the optimization process for mapping, we integrate additional supervision signals including easy-to-obtain monocular geometric cues and optical flow, and also introduce a simple warping loss to further enforce geometry consistency. Moreover, to further boost performance in complicated indoor scenes, we also propose a local adaptive transformation from signed distance functions (SDFs) to density in the volume rendering equation. On both synthetic and real-world datasets we demonstrate strong performance in dense mapping, tracking, and novel view synthesis, even competitive with recent RGB-D SLAM systems.
Prof. Emily M. Bender(she/her)
Wolfgang Lucht
jonny (good kind)
Daniel Lakens
Dmytro Mishkin 🇺🇦