Skip to search formSkip to main contentSkip to account menu

IBRNet: Learning Multi-View Image-Based Rendering

A method that synthesizes novel views of complex scenes by interpolating a sparse set of nearby views using a network architecture that includes a multilayer perceptron and a ray transformer that estimates radiance and volume density at continuous 5D locations.
View on IEEE (opens in a new tab)

Unsupervised Training for 3D Morphable Model Regression

This work introduces three objectives: a batch distribution loss that encourages the output distribution to match the distribution of the morphable model, a loopback loss that ensures the network can correctly reinterpret its own output, and a multi-view identity loss that compares the features of the predicted 3D face and the input photograph from multiple viewing angles.
View on IEEE (opens in a new tab)

Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation

A simple but surprisingly effective visual recognition benchmark for studying bias mitigation, and a simple but similarly effective alternative to the inference-time Reducing Bias Amplification method of Zhao et al., and design a domain-independent training technique that outperforms all other methods.
View on IEEE (opens in a new tab)

CvxNet: Learnable Convex Decomposition

This work introduces a network architecture to represent a low dimensional family of convexes, automatically derived via an auto-encoding process, and investigates the applications including automatic convex decomposition, image to 3D reconstruction, and part-based shape retrieval.
View on IEEE (opens in a new tab)

Learning Shape Templates With Structured Implicit Functions

It is shown that structured implicit functions are suitable for learning and allow a network to smoothly and simultaneously fit multiple classes of shapes in a general shape template from data.
View on IEEE (opens in a new tab)

Text-based editing of talking-head video

This work proposes a novel method to edit talking-head video based on its transcript to produce a realistic output video in which the dialogue of the speaker has been modified, while maintaining a seamless audio-visual flow (i.e. no jump cuts).
View on ACM (opens in a new tab)

Local Deep Implicit Functions for 3D Shape

Local Deep Implicit Functions (LDIF), a 3D shape representation that decomposes space into a structured set of learned implicit functions that provides higher surface reconstruction accuracy than the state-of-the-art (OccNet), while requiring fewer than 1\% of the network parameters.
View on IEEE (opens in a new tab)

NeSF: Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenes

The NeSF method is the first to learn semantics by recognizing patterns in the geometry stored within a 3D neural field representation, and generalizes to novel scenes, and requires as little as one semantic map per scene at training time.
View PDF on arXiv (opens in a new tab)

Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation

Panoptic Neural Fields is presented, an object-aware neural scene representation that decomposes a scene into a set of objects (things) and background (stuff) that can be smaller and faster than previous object- aware approaches, while still leveraging category-specific priors incorporated via meta-learned initialization.
View on IEEE (opens in a new tab)

Deep Structured Implicit Functions

Deep Structured Implicit Functions (DSIF), a 3D shape representation that decomposes space into a structured set of local deep implicit functions that provides 10.3 points higher surface reconstruction accuracy than the state-of-the-art (OccNet), while requiring fewer than 1 percent of the network parameters.
View PDF on arXiv (opens in a new tab)
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)