Search Results for author:
Found 28 papers, 16 papers with code
I$^2$-SLAM: Inverting Imaging Process for Robust Photorealistic Dense SLAM
We present an inverse image-formation module that can enhance the robustness of existing visual SLAM pipelines for casually captured scenarios.
Outdoor Scene Extrapolation with Hierarchical Generative Cellular Automata
We aim to generate fine-grained 3D geometry from large-scale sparse LiDAR scans, abundantly captured by autonomous vehicles (AV).
Fully Geometric Panoramic Localization
We introduce a lightweight and accurate localization method that only utilizes the geometry of 2D-3D lines.
3Doodle: Compact Abstraction of Objects with 3D Strokes
We propose 3Dooole, generating descriptive and view-consistent sketch images given multi-view images of the target object.
Text2Scene: Text-driven Indoor Scene Stylization with Part-aware Details
We propose Text2Scene, a method to automatically create realistic textures for virtual scenes composed of multiple objects.
Calibrating Panoramic Depth Estimation for Practical Localization and Mapping
While panoramic images can easily capture the surrounding context from commodity devices, the estimated depth shares the limitations of conventional image-based depth estimation; the performance deteriorates under large domain shifts and the absolute values are still ambiguous to infer from 2D observations.
LDL: Line Distance Functions for Panoramic Localization
We introduce LDL, a fast and robust algorithm that localizes a panorama to a 3D map using line segments.
Transformed Protoform Reconstruction
We update their model with the state-of-the-art seq2seq model: the Transformer.
PMP: Learning to Physically Interact with Environments using Part-wise Motion Priors
The proposed PMP allows us to assemble multiple part skills to animate a character, creating a diverse set of motions with different combinations of existing data.
Balanced Spherical Grid for Egocentric View Synthesis
However, the na\"ive spherical grid suffers from irregularities at two poles, and also cannot represent unbounded scenes.
Dynamic Mesh Recovery from Partial Point Cloud Sequence
The exact 3D dynamics of the human body provides crucial evidence to analyze the consequences of the physical interaction between the body and the environment, which can eventually assist everyday activities in a wide range of applications.
Privacy-Preserving Visual Localization with Event Cameras
We present a robust, privacy-preserving visual localization algorithm using event cameras.
MoDA: Map style transfer for self-supervised Domain Adaptation of embodied agents
We propose a domain adaptation method, MoDA, which adapts a pretrained embodied agent to a new, noisy environment without ground-truth supervision.
IBL-NeRF: Image-Based Lighting Formulation of Neural Radiance Fields
However, they are limited to representing isolated objects with a shared environment lighting, and suffer from computational burden to aggregate rays with Monte Carlo integration.
CPO: Change Robust Panorama to Point Cloud Localization
By utilizing the unique equivariance of spherical projections, we propose very fast color histogram generation for a large number of camera poses without explicitly rendering images for all candidate poses.
Ev-NeRF: Event Based Neural Radiance Field
We present Ev-NeRF, a Neural Radiance Field derived from event data.
Probabilistic Implicit Scene Completion
We also demonstrate that our approach outperforms deterministic models even in less ambiguous cases with a small amount of missing data, which infers that probabilistic formulation is crucial for high-quality geometry completion on input scans exhibiting any levels of completeness.
Ev-TTA: Test-Time Adaptation for Event-Based Object Recognition
We introduce Ev-TTA, a simple, effective test-time adaptation algorithm for event-based object recognition.
Ranked #1 on
Robust classification
on N-ImageNet
Neural Marionette: Unsupervised Learning of Motion Skeleton and Latent Dynamics from Volumetric Video
We present Neural Marionette, an unsupervised approach that discovers the skeletal structure from a dynamic sequence and learns to generate diverse motions that are consistent with the observed motion dynamics.
N-ImageNet: Towards Robust, Fine-Grained Object Recognition with Event Cameras
We introduce N-ImageNet, a large-scale dataset targeted for robust, fine-grained object recognition with event cameras.
Ranked #1 on
Classification
on N-ImageNet (mini)
SGoLAM: Simultaneous Goal Localization and Mapping for Multi-Object Goal Navigation
We present SGoLAM, short for simultaneous goal localization and mapping, which is a simple and efficient algorithm for Multi-Object Goal navigation.
Self-Supervised Domain Adaptation for Visual Navigation with Global Map Consistency
We propose a light-weight, self-supervised adaptation for a visual navigation agent to generalize to unseen environment.
PICCOLO: Point Cloud-Centric Omnidirectional Localization
Our loss function, called sampling loss, is point cloud-centric, evaluated at the projected location of every point in the point cloud.
GATSBI: Generative Agent-centric Spatio-temporal Object Interaction
We present GATSBI, a generative model that can transform a sequence of raw observations into a structured latent representation that fully captures the spatio-temporal context of the agent's actions.
Learning to Generate 3D Shapes with Generative Cellular Automata
We formulate the shape generation process as sampling from the transition kernel of a Markov chain, where the sampling chain eventually evolves to the full shape of the learned distribution.
Structure-From-Sherds: Incremental 3D Reassembly of Axially Symmetric Pots From Unordered and Mixed Fragment Collections
Motivated by the success of the incremental approach in robust SfM, we present an efficient reassembly method for axially symmetric pots based on iterative registration of one sherd at a time.
Spatial Semantic Embedding Network: Fast 3D Instance Segmentation with Deep Metric Learning
We propose spatial semantic embedding network (SSEN), a simple, yet efficient algorithm for 3D instance segmentation using deep metric learning.
RL-GAN-Net: A Reinforcement Learning Agent Controlled GAN Network for Real-Time Point Cloud Shape Completion
While a GAN is unstable and hard to train, we circumvent the problem by (1) training the GAN on the latent space representation whose dimension is reduced compared to the raw point cloud input and (2) using an RL agent to find the correct input to the GAN to generate the latent space representation of the shape that best fits the current input of incomplete point cloud.
