Related papers: Continual Neural Mapping: Learning An Implicit Sce…
This paper presents to the best of our knowledge the first end-to-end object tracking approach which directly maps from raw sensor input to object tracks in sensor space without requiring any feature engineering or system identification in…
Implicit neural representations (INRs) mark a fundamental shift in signal modeling, moving from discrete sampled data to continuous functional representations. By parameterizing signals as neural networks, INRs provide a unified framework…
Neural implicit surface representations have recently emerged as popular alternative to explicit 3D object encodings, such as polygonal meshes, tabulated points, or voxels. While significant work has improved the geometric fidelity of these…
Traditionally, training neural networks to perform semantic segmentation required expensive human-made annotations. But more recently, advances in the field of unsupervised learning have made significant progress on this issue and towards…
We present a novel method, called NeuralUDF, for reconstructing surfaces with arbitrary topologies from 2D images via volume rendering. Recent advances in neural rendering based reconstruction have achieved compelling results. However,…
3D scene segmentation based on neural implicit representation has emerged recently with the advantage of training only on 2D supervision. However, existing approaches still requires expensive per-scene optimization that prohibits…
Dashboard cameras capture a tremendous amount of driving scene video each day. These videos are purposefully coupled with vehicle sensing data, such as from the speedometer and inertial sensors, providing an additional sensing modality for…
We consider the problem of depth estimation from a single monocular image in this work. It is a challenging task as no reliable depth cues are available, e.g., stereo correspondences, motions, etc. Previous efforts have been focusing on…
In recent years, neural distance functions trained via volumetric ray marching have been widely adopted for multi-view 3D reconstruction. These methods, however, apply the ray marching procedure for the entire scene volume, leading to…
Implicit neural representation (INR) has proven to be accurate and efficient in various domains. In this work, we explore how different neural networks can be designed as a new texture INR, which operates in a continuous manner rather than…
In this paper, we address the "dual problem" of multi-view scene reconstruction in which we utilize single-view images captured under different point lights to learn a neural scene representation. Different from existing single-view methods…
Semantic labelling is highly correlated with geometry and radiance reconstruction, as scene entities with similar shape and appearance are more likely to come from similar classes. Recent implicit neural reconstruction techniques are…
Implicit Neural Representations have gained prominence as a powerful framework for capturing complex data modalities, encompassing a wide range from 3D shapes to images and audio. Within the realm of 3D shape representation, Neural Signed…
We describe in this short note a technique to convert an implicit surface into a Signed Distance Function (SDF) while exactly preserving the zero level-set of the implicit. The proposed approach relies on embedding the input implicit in the…
Deep neural networks (DNNs) are widely applied for nowadays 3D surface reconstruction tasks and such methods can be further divided into two categories, which respectively warp templates explicitly by moving vertices or represent 3D…
This paper proposes a deep-learning-based method for recovering a signed distance function (SDF) of a given hypersurface represented by an implicit level set function. Using the flexibility of constructing a neural network, we use an…
We present a method to automatically compute correct gradients with respect to geometric scene parameters in neural SDF renderers. Recent physically-based differentiable rendering techniques for meshes have used edge-sampling to handle…
Scene Completion is the task of completing missing geometry from a partial scan of a scene. Most previous methods compute an implicit representation from range data using a Truncated Signed Distance Function (T-SDF) computed on a 3D grid as…
In continual learning (CL), a learner is faced with a sequence of tasks, arriving one after the other, and the goal is to remember all the tasks once the continual learning experience is finished. The prior art in CL uses episodic memory,…
We present a novel neural surface reconstruction method, called NeuS, for reconstructing objects and scenes with high fidelity from 2D image inputs. Existing neural surface reconstruction approaches, such as DVR and IDR, require foreground…