Search Results for author:
Found 28 papers, 11 papers with code
From Activation to Initialization: Scaling Insights for Optimizing Neural Fields
In the realm of computer vision, Neural Fields have gained prominence as a contemporary tool harnessing neural networks for signal representation.
Backpropagation-free Network for 3D Test-time Adaptation
Here, we propose a novel method that uses a backpropagation-free approach for TTA for the specific case of 3D data.
ViewFusion: Towards Multi-View Consistency via Interpolated Denoising
Novel-view synthesis through diffusion models has demonstrated remarkable potential for generating diverse and high-quality images.
A Sampling Theory Perspective on Activations for Implicit Neural Representations
Implicit Neural Representations (INRs) have gained popularity for encoding signals as compact, differentiable entities.
LumiNet: The Bright Side of Perceptual Knowledge Distillation
In knowledge distillation literature, feature-based methods have dominated due to their ability to effectively tap into extensive teacher models.
Ranked #1 on
Classification
on CIFAR-100
Robust Point Cloud Processing through Positional Embedding
End-to-end trained per-point embeddings are an essential ingredient of any state-of-the-art 3D point cloud processing such as detection or alignment.
Curvature-Aware Training for Coordinate Networks
Coordinate networks are widely used in computer vision due to their ability to represent signals as compressed, continuous entities.
On the effectiveness of neural priors in modeling dynamical systems
Modelling dynamical systems is an integral component for understanding the natural world.
BLiRF: Bandlimited Radiance Fields for Dynamic Scene Modeling
Reasoning the 3D structure of a non-rigid dynamic scene from a single moving camera is an under-constrained problem.
How You Start Matters for Generalization
Characterizing the remarkable generalization properties of over-parameterized neural networks remains an open problem.
Few-shot Class-incremental Learning for 3D Point Cloud Objects
Few-shot class-incremental learning (FSCIL) aims to incrementally fine-tune a model (trained on base classes) for a novel set of classes using a few examples without forgetting the previous training.
Trading Positional Complexity vs. Deepness in Coordinate Networks
It is well noted that coordinate-based MLPs benefit -- in terms of preserving high-frequency information -- through the encoding of coordinate positions as an array of Fourier features.
GARF: Gaussian Activated Radiance Fields for High Fidelity Reconstruction and Pose Estimation
Despite Neural Radiance Fields (NeRF) showing compelling results in photorealistic novel views synthesis of real-world scenes, most existing approaches require accurate prior camera poses.
On Regularizing Coordinate-MLPs
We show that typical implicit regularization assumptions for deep neural networks (for regression) do not hold for coordinate-MLPs, a family of MLPs that are now ubiquitous in computer vision for representing high-frequency signals.
Learning Positional Embeddings for Coordinate-MLPs
We propose a novel method to enhance the performance of coordinate-MLPs by learning instance-specific positional embeddings.
Beyond Periodicity: Towards a Unifying Framework for Activations in Coordinate-MLPs
Coordinate-MLPs are emerging as an effective tool for modeling multidimensional continuous signals, overcoming many drawbacks associated with discrete grid-based approximations.
Enabling equivariance for arbitrary Lie groups
Our framework enables the implementation of group convolutions over any finite-dimensional Lie group.
Rethinking Positional Encoding
It is well noted that coordinate based MLPs benefit -- in terms of preserving high-frequency information -- through the encoding of coordinate positions as an array of Fourier features.
Robust normalizing flows using Bernstein-type polynomials
Modeling real-world distributions can often be challenging due to sample data that are subjected to perturbations, e. g., instrumentation errors, or added random noise.
Synthesized Feature Based Few-Shot Class-Incremental Learning on a Mixture of Subspaces
In this paper, we propose addressing this problem using a mixture of subspaces.
Rethinking conditional GAN training: An approach using geometrically structured latent manifolds
Conditional GANs (cGAN), in their rudimentary form, suffer from critical drawbacks such as the lack of diversity in generated outputs and distortion between the latent and output manifolds.
Conditional Generative Modeling via Learning the Latent Space
Although deep learning has achieved appealing results on several machine learning tasks, most of the models are deterministic at inference, limiting their application to single-modal settings.
Spectral-GANs for High-Resolution 3D Point-cloud Generation
Point-clouds are a popular choice for vision and graphics tasks due to their accurate shape description and direct acquisition from range-scanners.
Representation Learning on Unit Ball with 3D Roto-Translational Equivariance
In this work, we propose a novel `\emph{volumetric convolution}' operation that can effectively model and convolve arbitrary functions in $\mathbb{B}^3$.
Blended Convolution and Synthesis for Efficient Discrimination of 3D Shapes
Existing networks directly learn feature representations on 3D point clouds for shape analysis.
Volumetric Convolution: Automatic Representation Learning in Unit Ball
Convolution is an efficient technique to obtain abstract feature representations using hierarchical layers in deep networks.
Combined Static and Motion Features for Deep-Networks Based Activity Recognition in Videos
We propose three schemas for combining static and motion components: based on a variance ratio, principal components, and Cholesky decomposition.
A Context-aware Capsule Network for Multi-label Classification
Recently proposed Capsule Network is a brain inspired architecture that brings a new paradigm to deep learning by modelling input domain variations through vector based representations.
