DynOMo: Online Point Tracking by Dynamic Online Monocular Gaussian Reconstruction

Reconstructing scenes and tracking motion are two sides of the same coin. Tracking points allow for geometric reconstruction [14], while geometric reconstruction of (dynamic) scenes allows for 3D tracking of points over time [24, 39]. The latter was recently also exploited for 2D point tracking to overcome occlusion ambiguities by lifting tracking directly into 3D [38]. However, above approaches either require offline processing or multi-view camera setups both unrealistic for real-world applications like robot navigation or mixed reality. We target the challenge of online 2D and 3D point tracking from unposed monocular camera input introducing Dynamic Online Monocular Reconstruction (DynOMo). We leverage 3D Gaussian splatting to reconstruct dynamic scenes in an online fashion. Our approach extends 3D Gaussians to capture new content and object motions while estimating camera movements from a single RGB frame. DynOMo stands out by enabling emergence of point trajectories through robust image feature reconstruction and a novel similarity-enhanced regularization term, without requiring any correspondence-level supervision. It sets the first baseline for online point tracking with monocular unposed cameras, achieving performance on par with existing methods. We aim to inspire the community to advance online point tracking and reconstruction, expanding the applicability to diverse real-world scenarios.

GenAI-Bench: Evaluating and Improving Compositional Text-to-Visual Generation

While text-to-visual models now produce photo-realistic images and videos, they struggle with compositional text prompts involving attributes, relationships, and higher-order reasoning such as logic and comparison. In this work, we conduct an extensive human study on GenAI-Bench to evaluate the performance of leading image and video generation models in various aspects of compositional text-to-visual generation. We also compare automated evaluation metrics against our collected human ratings and find that VQAScore -- a metric measuring the likelihood that a VQA model views an image as accurately depicting the prompt -- significantly outperforms previous metrics such as CLIPScore. In addition, VQAScore can improve generation in a black-box manner (without finetuning) via simply ranking a few (3 to 9) candidate images. Ranking by VQAScore is 2x to 3x more effective than other scoring methods like PickScore, HPSv2, and ImageReward at improving human alignment ratings for DALL-E 3 and Stable Diffusion, especially on compositional prompts that require advanced visio-linguistic reasoning. We will release a new GenAI-Rank benchmark with over 40,000 human ratings to evaluate scoring metrics on ranking images generated from the same prompt. Lastly, we discuss promising areas for improvement in VQAScore, such as addressing fine-grained visual details. We will release all human ratings (over 80,000) to facilitate scientific benchmarking of both generative models and automated metrics.

Simultaneous Map and Object Reconstruction

In this paper, we present a method for dynamic surface reconstruction of large-scale urban scenes from LiDAR. Depth-based reconstructions tend to focus on small-scale objects or large-scale SLAM reconstructions that treat moving objects as outliers. We take a holistic perspective and optimize a compositional model of a dynamic scene that decomposes the world into rigidly moving objects and the background. To achieve this, we take inspiration from recent novel view synthesis methods and pose the reconstruction problem as a global optimization, minimizing the distance between our predicted surface and the input LiDAR scans. We show how this global optimization can be decomposed into registration and surface reconstruction steps, which are handled well by off-the-shelf methods without any re-training. By careful modeling of continuous-time motion, our reconstructions can compensate for the rolling shutter effects of rotating LiDAR sensors. This allows for the first system (to our knowledge) that properly motion compensates LiDAR scans for rigidly-moving objects, complementing widely-used techniques for motion compensation of static scenes. Beyond pursuing dynamic reconstruction as a goal in and of itself, we also show that such a system can be used to auto-label partially annotated sequences and produce ground truth annotation for hard-to-label problems such as depth completion and scene flow.

Planning with Adaptive World Models for Autonomous Driving

Motion planning is crucial for safe navigation in complex urban environments. Historically, motion planners (MPs) have been evaluated with procedurally-generated simulators like CARLA. However, such synthetic benchmarks do not capture real-world multi-agent interactions. nuPlan, a recently released MP benchmark, addresses this limitation by augmenting real-world driving logs with closed-loop simulation logic, effectively turning the fixed dataset into a reactive simulator. We analyze the characteristics of nuPlan's recorded logs and find that each city has its own unique driving behaviors, suggesting that robust planners must adapt to different environments. We learn to model such unique behaviors with BehaviorNet, a graph convolutional neural network (GCNN) that predicts reactive agent behaviors using features derived from recently-observed agent histories; intuitively, some aggressive agents may tailgate lead vehicles, while others may not. To model such phenomena, BehaviorNet predicts parameters of an agent's motion controller rather than predicting its spacetime trajectory (as most forecasters do). Finally, we present AdaptiveDriver, a model-predictive control (MPC) based planner that unrolls different world models conditioned on BehaviorNet's predictions. Our extensive experiments demonstrate that AdaptiveDriver achieves state-of-the-art results on the nuPlan closed-loop planning benchmark, reducing test error from 6.4% to 4.6%, even when applied to never-before-seen cities.

Shelf-Supervised Multi-Modal Pre-Training for 3D Object Detection

State-of-the-art 3D object detectors are often trained on massive labeled datasets. However, annotating 3D bounding boxes remains prohibitively expensive and time-consuming, particularly for LiDAR. Instead, recent works demonstrate that self-supervised pre-training with unlabeled data can improve detection accuracy with limited labels. Contemporary methods adapt best-practices for self-supervised learning from the image domain to point clouds (such as contrastive learning). However, publicly available 3D datasets are considerably smaller and less diverse than those used for image-based self-supervised learning, limiting their effectiveness. We do note, however, that such data is naturally collected in a multimodal fashion, often paired with images. Rather than pre-training with only self-supervised objectives, we argue that it is better to bootstrap point cloud representations using image-based foundation models trained on internet-scale image data. Specifically, we propose a shelf-supervised approach (e.g. supervised with off-the-shelf image foundation models) for generating zero-shot 3D bounding boxes from paired RGB and LiDAR data. Pre-training 3D detectors with such pseudo-labels yields significantly better semi-supervised detection accuracy than prior self-supervised pretext tasks. Importantly, we show that image-based shelf-supervision is helpful for training LiDAR-only and multi-modal (RGB + LiDAR) detectors. We demonstrate the effectiveness of our approach on nuScenes and WOD, significantly improving over prior work in limited data settings.

Neural Representations of Dynamic Visual Stimuli

Humans experience the world through constantly changing visual stimuli, where scenes can shift and move, change in appearance, and vary in distance. The dynamic nature of visual perception is a fundamental aspect of our daily lives, yet the large majority of research on object and scene processing, particularly using fMRI, has focused on static stimuli. While studies of static image perception are attractive due to their computational simplicity, they impose a strong non-naturalistic constraint on our investigation of human vision. In contrast, dynamic visual stimuli offer a more ecologically-valid approach but present new challenges due to the interplay between spatial and temporal information, making it difficult to disentangle the representations of stable image features and motion. To overcome this limitation -- given dynamic inputs, we explicitly decouple the modeling of static image representations and motion representations in the human brain. Three results demonstrate the feasibility of this approach. First, we show that visual motion information as optical flow can be predicted (or decoded) from brain activity as measured by fMRI. Second, we show that this predicted motion can be used to realistically animate static images using a motion-conditioned video diffusion model (where the motion is driven by fMRI brain activity). Third, we show prediction in the reverse direction: existing video encoders can be fine-tuned to predict fMRI brain activity from video imagery, and can do so more effectively than image encoders. This foundational work offers a novel, extensible framework for interpreting how the human brain processes dynamic visual information.

Predicting Long-horizon Futures by Conditioning on Geometry and Time

Our work explores the task of generating future sensor observations conditioned on the past. We are motivated by `predictive coding' concepts from neuroscience as well as robotic applications such as self-driving vehicles. Predictive video modeling is challenging because the future may be multi-modal and learning at scale remains computationally expensive for video processing. To address both challenges, our key insight is to leverage the large-scale pretraining of image diffusion models which can handle multi-modality. We repurpose image models for video prediction by conditioning on new frame timestamps. Such models can be trained with videos of both static and dynamic scenes. To allow them to be trained with modestly-sized datasets, we introduce invariances by factoring out illumination and texture by forcing the model to predict (pseudo) depth, readily obtained for in-the-wild videos via off-the-shelf monocular depth networks. In fact, we show that simply modifying networks to predict grayscale pixels already improves the accuracy of video prediction. Given the extra controllability with timestamp conditioning, we propose sampling schedules that work better than the traditional autoregressive and hierarchical sampling strategies. Motivated by probabilistic metrics from the object forecasting literature, we create a benchmark for video prediction on a diverse set of videos spanning indoor and outdoor scenes and a large vocabulary of objects. Our experiments illustrate the effectiveness of learning to condition on timestamps, and show the importance of predicting the future with invariant modalities.

Evaluating Text-to-Visual Generation with Image-to-Text Generation

Despite significant progress in generative AI, comprehensive evaluation remains challenging because of the lack of effective metrics and standardized benchmarks. For instance, the widely-used CLIPScore measures the alignment between a (generated) image and text prompt, but it fails to produce reliable scores for complex prompts involving compositions of objects, attributes, and relations. One reason is that text encoders of CLIP can notoriously act as a "bag of words", conflating prompts such as "the horse is eating the grass" with "the grass is eating the horse". To address this, we introduce the VQAScore, which uses a visual-question-answering (VQA) model to produce an alignment score by computing the probability of a "Yes" answer to a simple "Does this figure show '{text}'?" question. Though simpler than prior art, VQAScore computed with off-the-shelf models produces state-of-the-art results across many (8) image-text alignment benchmarks. We also compute VQAScore with an in-house model that follows best practices in the literature. For example, we use a bidirectional image-question encoder that allows image embeddings to depend on the question being asked (and vice versa). Our in-house model, CLIP-FlanT5, outperforms even the strongest baselines that make use of the proprietary GPT-4V. Interestingly, although we train with only images, VQAScore can also align text with video and 3D models. VQAScore allows researchers to benchmark text-to-visual generation using complex texts that capture the compositional structure of real-world prompts. We introduce GenAI-Bench, a more challenging benchmark with 1,600 compositional text prompts that require parsing scenes, objects, attributes, relationships, and high-order reasoning like comparison and logic. GenAI-Bench also offers over 15,000 human ratings for leading image and video generation models such as Stable Diffusion, DALL-E 3, and Gen2.

Better Call SAL: Towards Learning to Segment Anything in Lidar

We propose $\texttt{SAL}$ ($\texttt{S}$egment $\texttt{A}$nything in $\texttt{L}$idar) method consisting of a text-promptable zero-shot model for segmenting and classifying any object in Lidar, and a pseudo-labeling engine that facilitates model training without manual supervision. While the established paradigm for $\textit{Lidar Panoptic Segmentation}$ (LPS) relies on manual supervision for a handful of object classes defined a priori, we utilize 2D vision foundation models to generate 3D supervision "for free". Our pseudo-labels consist of instance masks and corresponding CLIP tokens, which we lift to Lidar using calibrated multi-modal data. By training our model on these labels, we distill the 2D foundation models into our Lidar $\texttt{SAL}$ model. Even without manual labels, our model achieves $91\%$ in terms of class-agnostic segmentation and $44\%$ in terms of zero-shot LPS of the fully supervised state-of-the-art. Furthermore, we outperform several baselines that do not distill but only lift image features to 3D. More importantly, we demonstrate that $\texttt{SAL}$ supports arbitrary class prompts, can be easily extended to new datasets, and shows significant potential to improve with increasing amounts of self-labeled data.

I Can't Believe It's Not Scene Flow!

Current scene flow methods broadly fail to describe motion on small objects, and current scene flow evaluation protocols hide this failure by averaging over many points, with most drawn larger objects. To fix this evaluation failure, we propose a new evaluation protocol, Bucket Normalized EPE, which is class-aware and speed-normalized, enabling contextualized error comparisons between object types that move at vastly different speeds. To highlight current method failures, we propose a frustratingly simple supervised scene flow baseline, TrackFlow, built by bolting a high-quality pretrained detector (trained using many class rebalancing techniques) onto a simple tracker, that produces state-of-the-art performance on current standard evaluations and large improvements over prior art on our new evaluation. Our results make it clear that all scene flow evaluations must be class and speed aware, and supervised scene flow methods must address point class imbalances. We release the evaluation code publicly at https://github.com/kylevedder/BucketedSceneFlowEval.