Nerfdiff: Single-image view synthesis with nerf-guided distillation from 3d-aware diffusion
Novel view synthesis from a single image requires inferring occluded regions of objects and
scenes whilst simultaneously maintaining semantic and physical consistency with the input …
scenes whilst simultaneously maintaining semantic and physical consistency with the input …
Neural fields in visual computing and beyond
Recent advances in machine learning have led to increased interest in solving visual
computing problems using methods that employ coordinate‐based neural networks. These …
computing problems using methods that employ coordinate‐based neural networks. These …
Segment anything in 3d with nerfs
Abstract Recently, the Segment Anything Model (SAM) emerged as a powerful vision
foundation model which is capable to segment anything in 2D images. This paper aims to …
foundation model which is capable to segment anything in 2D images. This paper aims to …
Object scene representation transformer
MSM Sajjadi, D Duckworth… - Advances in …, 2022 - proceedings.neurips.cc
A compositional understanding of the world in terms of objects and their geometry in 3D
space is considered a cornerstone of human cognition. Facilitating the learning of such a …
space is considered a cornerstone of human cognition. Facilitating the learning of such a …
Weakly supervised 3d open-vocabulary segmentation
Open-vocabulary segmentation of 3D scenes is a fundamental function of human perception
and thus a crucial objective in computer vision research. However, this task is heavily …
and thus a crucial objective in computer vision research. However, this task is heavily …
Conditional object-centric learning from video
Object-centric representations are a promising path toward more systematic generalization
by providing flexible abstractions upon which compositional world models can be built …
by providing flexible abstractions upon which compositional world models can be built …
Feature 3dgs: Supercharging 3d gaussian splatting to enable distilled feature fields
Abstract 3D scene representations have gained immense popularity in recent years.
Methods that use Neural Radiance fields are versatile for traditional tasks such as novel …
Methods that use Neural Radiance fields are versatile for traditional tasks such as novel …
Simple unsupervised object-centric learning for complex and naturalistic videos
Unsupervised object-centric learning aims to represent the modular, compositional, and
causal structure of a scene as a set of object representations and thereby promises to …
causal structure of a scene as a set of object representations and thereby promises to …
Learning multi-object dynamics with compositional neural radiance fields
We present a method to learn compositional multi-object dynamics models from image
observations based on implicit object encoders, Neural Radiance Fields (NeRFs), and …
observations based on implicit object encoders, Neural Radiance Fields (NeRFs), and …
Fwd: Real-time novel view synthesis with forward warping and depth
Novel view synthesis (NVS) is a challenging task requiring systems to generate
photorealistic images of scenes from new viewpoints, where both quality and speed are …
photorealistic images of scenes from new viewpoints, where both quality and speed are …