Related papers: Efficient Construction of Implicit Surface Models …
Despite advancements in Neural Implicit models for 3D surface reconstruction, handling dynamic environments with interactions between arbitrary rigid, non-rigid, or deformable entities remains challenging. The generic reconstruction methods…
Neural implicit surface reconstruction with signed distance function has made significant progress, but recovering fine details such as thin structures and complex geometries remains challenging due to unreliable or noisy geometric priors.…
Neural reconstruction models for autonomous driving simulation have made significant strides in recent years, with dynamic models becoming increasingly prevalent. However, these models are typically limited to handling in-domain objects…
Implicit neural representation has opened up new possibilities for inverse rendering. However, existing implicit neural inverse rendering methods struggle to handle strongly illuminated scenes with significant shadows and indirect…
Three-dimensional (3D) freehand ultrasound (US) is a widely used imaging modality that allows non-invasive imaging of medical anatomy without radiation exposure. Surface reconstruction of US volume is vital to acquire the accurate…
Robots benefit from high-fidelity reconstructions of their environment, which should be geometrically accurate and photorealistic to support downstream tasks. While this can be achieved by building distance fields from range sensors and…
Indirect image registration is a promising technique to improve image reconstruction quality by providing a shape prior for the reconstruction task. In this paper, we propose a novel hybrid method that seeks to reconstruct high quality…
We present a unified and compact scene representation for robotics, where each object in the scene is depicted by a latent code capturing geometry and appearance. This representation can be decoded for various tasks such as novel view…
Large-scale numerical simulations are capable of generating data up to terabytes or even petabytes. As a promising method of data reduction, super-resolution (SR) has been widely studied in the scientific visualization community. However,…
Intrinsic decomposition from a single image is a highly challenging task, due to its inherent ambiguity and the scarcity of training data. In contrast to traditional fully supervised learning approaches, in this paper we propose learning…
Multimode fibers (MMFs) have the potential to carry complex images for endoscopy and related applications, but decoding the complex speckle patterns produced by mode-mixing and modal dispersion in MMFs is a serious challenge. Several groups…
Neural Radiance Fields (NeRF) have constituted a remarkable breakthrough in image-based 3D reconstruction. However, their implicit volumetric representations differ significantly from the widely-adopted polygonal meshes and lack support…
Implicit surfaces via neural radiance fields (NeRF) have shown surprising accuracy in surface reconstruction. Despite their success in reconstructing richly textured surfaces, existing methods struggle with planar regions with weak…
Neural implicit reconstruction via volume rendering has demonstrated its effectiveness in recovering dense 3D surfaces. However, it is non-trivial to simultaneously recover meticulous geometry and preserve smoothness across regions with…
Implicit neural representations (INRs) have emerged as a powerful tool for solving inverse problems in computer vision and computational imaging. INRs represent images as continuous domain functions realized by a neural network taking…
Models for image representation learning are typically designed for either recognition or generation. Various forms of contrastive learning help models learn to convert images to embeddings that are useful for classification, detection, and…
Feature-Imitating-Networks (FINs) are neural networks that are first trained to approximate closed-form statistical features (e.g. Entropy), and then embedded into other networks to enhance their performance. In this work, we perform the…
Single-image 3D human reconstruction aims to reconstruct the 3D textured surface of the human body given a single image. While implicit function-based methods recently achieved reasonable reconstruction performance, they still bear…
Deep implicit functions have shown remarkable shape modeling ability in various 3D computer vision tasks. One drawback is that it is hard for them to represent a 3D shape as multiple parts. Current solutions learn various primitives and…
Implicit neural representations (INRs) have emerged as a powerful tool for solving inverse problems in computer vision and computational imaging. INRs represent images as continuous domain functions realized by a neural network taking…