fangjinhuawang.github.io
VolRecon: Volume Rendering of Signed Ray Distance Functions for Generalizable Multi-View Reconstruction
· Yufan Ren1 *, Fangjinhua Wang2 *, Tong Zhang1, Marc Pollefeys2,3, Sabine Süsstrunk1 * Equal Contribution 1EPFL 2ETH Zurich 3Microsoft Mixed Reality & AI Zurich Lab · Shared by 5, including Matt Shaffer
people.eecs.berkeley.edu
Cut and Learn for Unsupervised Object Detection and Instance Segmentation
· CutLER: Cut and Learn for Unsupervised Object Detection and Instance Segmentation Xudong Wang Rohit Girdhar Stella X. Yu Ishan Misra FAIR, Meta AI UC Berkeley / ICSI University of Michigan [Preprint]… · Shared by 8, including Matt Shaffer, Marktechpost AI Research News ⚡
sites.google.com
Home
10 min · · Foundation models have shown impressive adaptation and scalability in supervised and self-supervised learning problems, but so far these successes have not fully translated to reinforcement learning… · Shared by 18, including 瑞拿頭, Vikram Dutt, Matt Shaffer, Marktechpost AI Research News ⚡
laser-nv-paper.github.io
Laser: Latent Set Representations for 3D Generative Modeling
2 min · · NeRF provides unparalleled fidelity of novel view synthesis—rendering a 3D scene from an arbitrary viewpoint. NeRF requires training on a large number of views that fully cover a scene, which limits… · Shared by 8, including Marktechpost AI Research News ⚡, Matt Shaffer
AI Papers
End-to-End Imitation Learning with Safety Guarantees using Control Barrier Functions
1 min · · Imitation learning (IL) is a learning paradigm which can be used to synthesize controllers for complex systems that mimic behavior demonstrated by an expert (user or control algorithm). Despite their… · Shared by 4, including Matt Shaffer
AI Papers
Oracle Guided Image Synthesis with Relative Queries
1 min · · Isolating and controlling specific features in the outputs of generative models in a user-friendly way is a difficult and open-ended problem. We develop techniques that allow an oracle user to… · Shared by 5, including Matt Shaffer
Stanford University
See, Hear, Feel: Smart Sensory Fusion for Robotic Manipulation
1 min · · Abstract Humans use all of their senses to accomplish different tasks in everyday activities. In contrast, existing work on robotic manipulation mostly relies on one, or occasionally two modalities,… · Shared by 4, including Matt Shaffer
tuneavideo.github.io
Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation
· A new method for text-to-video generation using one text-video pair. · Shared by 4, including Matt Shaffer
threedle.github.io
3D Highlighter: Localizing Regions on 3D Shapes via Text Descriptions
· @article{decatur2022highlighter, author = {Decatur, Dale and Lang, Itai and Hanocka, Rana}, title = {3D Highlighter: Localizing Regions on 3D Shapes via Text Descriptions}, journal = {arXiv}, year =… · Shared by 4, including Matt Shaffer
snap-research.github.io
DiscoScene: Spatially Disentangled Generative Radiance Field for Controllable 3D-aware Scene Synthesis
· Yinghao Xu1,2, Menglei Chai2, Zifan Shi3, Sida Peng4, Ivan Skorokhodov5,2, Aliaksandr Siarohin2, Ceyuan Yang1, Yujun Shen1, Hsin-Ying Lee · Shared by 4, including Matt Shaffer
MIT CSAIL
Assemble Them All
· @article{tian2022assemble, title={Assemble Them All: Physics-Based Planning for Generalizable Assembly by Disassembly}, author={Tian, Yunsheng and Xu, Jie and Li, Yichen and Luo, Jieliang and Sueda,… · Shared by 5, including Matt Shaffer
sites.google.com
i-S2R
6 min · · High-Speed, Dynamic Table Tennis with Deep Reinforcement Learning! · Shared by 7, including Matt Shaffer
Demis Hassabis
From Data to Functa: Your data point is a function and you should treat it like one
1 min · · It is common practice in deep learning to represent a measurement of the world on a discrete grid, e.g. a 2D grid of pixels. However, the underlying signal represented by these measurements is often… · Shared by 6, including Matt Shaffer
mrtornado24.github.io
IDE-3D: Interactive Disentangled Editing for High-Resolution 3D-aware Portrait Synthesis
1 min · · Existing 3D-aware facial generation methods face a dilemma in quality ver- sus editability: they either generate editable results in low resolution, or high quality ones with no editing flexibility.… · Shared by 5, including Matt Shaffer
nesf3d.github.io
NeSF: Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenes
· TMLR 2022 Suhani Vora*1, Noha Radwan*1, Klaus Greff1, Henning Meyer1, Kyle Genova1, Mehdi S. M. Sajjadi1, Etienne Pott1 Andrea Tagliasacchi1,2 · Shared by 6, including Matt Shaffer