arXiv subjects

Juho Kannala

Publications and source records attributed to Juho Kannala.

At least 19 recordsLinked to original sources

arXiv2026

Does Attention-Guided Masking Really Help Object Discovery in Object-Centric Learning?

Object-Centric Learning (OCL) aims to decompose images into objects without human annotations. A major family of mainstream methods uses Slot Attention to aggregate image features into object-level representations and then from them reconstructs masked image content, i.e., Random Masking (RM), to provide self-supervision. The recent method DIAS simply masks image patches at uniform randomness yet achieves competitive object discovery accuracy. Since attention during aggregation already possesses object discovery ability, we explore using it to develop a better image patch masking strategy, i.e., Attention Guided Masking (AGM), thereby providing better self-supervision. Results on six recognized datasets show that AGM does not always outperform RM. Under unconditional slot initialization, AGM substantially improves background segmentation on datasets with realistic textures (COCO and VOC); Regardless of conditional or unconditional slot initialization and across datasets, foreground object discovery remains comparable or decreases. We suggest peer researchers in the OCL community that attempts to exploit internal attention semantics to improve OCL with masked decoding are risky. Our source code, model checkpoints and evaluation logs will be released upon acceptance.

cs.CV↗

arXiv2026

TileGS: Tile-Local Depth Binning for Gaussian Splatting Rasterization

Real-time 3D Gaussian Splatting (3DGS) achieves high rendering quality, but standard rasterization still traverses a globally sorted tile stream that creates long per-tile ranges and heavy geometry-attribute traffic. We present TileGS, a tile-local reorganization of Gaussian splatting. TileGS turns each long tile range into a sequence of shorter depth-local ranges, rasterizes those ranges in front-to-back order, and applies selective repair where coarse ordering is insufficient to match baseline compositing. Across a 9-scene benchmark on desktop and laptop Ada GPUs, our default No-GW (No Geometry-Write) variant delivers a mean 1.44x raster-kernel speedup on RTX 4090 and mean end-to-end frame speedups of 1.069x on RTX 4090 and 1.094x on RTX 1000 Ada over gsplat--a widely used optimized open-source 3DGS implementation--while matching the gsplat output up to numerical noise (|Delta PSNR| < 0.001 dB, |Delta SSIM| < 0.001, |Delta LPIPS| < 0.001). Full-suite RTX 4090 Nsight Compute profiling reveals TileGS is faster despite lower SM throughput, lower active-warp occupancy, and higher DRAM traffic, while total SASS thread instructions fall by 1.26x. Source-attributed profiling confirms that geometry attributes dominate the remaining memory pressure (85.8% of total raster traffic and 88.6% of excess sectors). Together, these counters support the interpretation that TileGS improves raster performance by reducing effective raster traversal work, rather than by reducing byte volume, improving coalescing, increasing occupancy, or directly reducing measured warp divergence.

cs.GR↗

arXiv2026

Compressing AI Traffic: Standardized Neural Network Coding of Visual-Token Representations in Split Vision-Language Inference

When the visual encoder and the language decoder of a vision-language model (VLM) run on different compute nodes, the intermediate visual-token embeddings become a communicated payload rather than an internal activation. We call such machine-consumed intermediate tensors AI traffic and ask how far they can be compressed with a standardized, training-free codec. We insert ISO/IEC 15938-17 Neural Network Coding (NNC) round trips on the complete visual interface of a Qwen3-VL-8B-Instruct video question answering pipeline, comprising the main visual-token representation and the DeepStack feature streams, while leaving weights, prompts, and generation untouched, and sweep the quantization parameter (QP) over a wide rate range. Closed-ended Video-MME accuracy remains close to the uncompressed reference up to a 98% reduction of the transmitted BF16 tensor and only then collapses; open-ended MLVU generation shows the same plateau-and-collapse profile under an LLM judge. This robustness is not due to near-lossless reconstruction: the decoded tensor is heavily discretized, carries substantial row-wise relative L2 error, and has a visibly steeper singular-value decay than its source. Downstream reasoning therefore depends on coarse structure and relative geometry rather than exact floating-point values, which argues for rate-task rather than rate-distortion optimization of AI traffic codecs.

cs.CV↗

arXiv2026

GeoMix: Descriptor-Free Visual Localization via Global Context and Multi-Detector Training

Descriptor-free visual localization eliminates high-dimensional descriptor storage, preserves scene privacy, and simplifies map maintenance, yet its accuracy still lags far behind descriptor-based pipelines. We identify this gap to insufficient geometric discriminability in geometry-only matching. Without visual appearance, current methods underutilize local geometry cues, lack the global context among keypoints, and overfit to a single keypoint detector. We further observe that descriptor-free matching naturally enables multi-detector training, as heterogeneous keypoints can be optimized in a shared geometry-only space without aligning descriptor spaces. Building on these insights, we propose GeoMix, a descriptor-free 2D-3D matching framework that strengthens geometric discriminability at three levels. Locally, directional and distance-aware embeddings enrich neighborhood aggregation with fine-grained spatial structure. Globally, learnable context nodes aggregate and redistribute scene-wide information via cross-attention to resolve ambiguities beyond local receptive fields. At the training level, Mix-Training exploits this detector-agnostic geometry space to learn representations across multiple keypoint detectors. Extensive experiments on MegaDepth, Cambridge Landmarks, 7Scenes, and Aachen Day-Night show that GeoMix sets a new state of the art among descriptor-free methods, reducing 75th-percentile rotation error by 89\% and translation error by up to 90\% over the previous best, while generalizing zero-shot to unseen detectors and narrowing the gap to descriptor-based pipelines. Code is available at $\href{https://github.com/YejunZhang/Geomix}{\text{this links}}$.

cs.CV↗

arXiv2026

SplatGuide: Geometric Priors from 3D Gaussians for Pose-Free Novel View Synthesis

Generating photorealistic novel views from unposed images requires both 3D geometric understanding and the ability to synthesize unseen content. A natural strategy combines feed-forward 3DGS reconstruction with multi-view diffusion. Yet prior pipelines extract at most one signal from the reconstruction, either pixel rendering or learned features, while none exploits per-Gaussian visibility for occlusion-aware reference selection. This *information disconnect* leaves renderable geometry, visibility cues, and learned features unused. SplatGuide closes this disconnect by reusing a single 3DGS scene across three complementary roles. Rendered images provide pixel-aligned geometric conditioning. Per-Gaussian source-view indices are rendered into a target-view voting map for occlusion-aware reference selection. Reconstruction tokens supply feature-level guidance via cross-attention. All three signals derive from the same reconstruction forward pass. Across RealEstate10K, DL3DV, Tanks-and-Temples, and Mip-NeRF 360, SplatGuide achieves state-of-the-art pose-free novel view synthesis. On RealEstate10K, with a moderate number of input views, it surpasses the ground-truth-pose baseline.

cs.CV↗

arXiv2026

HSA: Hierarchical Slot Attention for Multi-granularity Scene-Decomposition

Slot attention is a powerful framework for object-centric learning, decomposing visual scenes into latent slots through iterative competitive attention. However, existing methods share two critical limitations: they decompose scenes into a flat set of slots at a single granularity, and this decomposition is based on appearance rather than semantics. Yet humans understand scenes through semantic hierarchies: separating foreground from background, recognizing object categories, and identifying individual instances. Crucially, such semantic hierarchies cannot emerge without supervision, because category names are human constructs, not visual patterns. We propose Hierarchical Slot Attention (HSA), which learns multi-granularity semantic scene decomposition from a single model. HSA decomposes scenes at three levels: holistic (foreground/background), semantic (object categories), and panoptic (individual instances). Using only 10\% labeled data, combined with hierarchical alignment loss, HSA learns all three levels jointly. We further introduce grouping purity and containment to measure whether the hierarchy is encoded in representation space, not just output masks. Experiments on COCO and PASCAL VOC demonstrate that HSA outperforms the strongest flat baseline by up to \textbf{$+$41.5} ARI at holistic, \textbf{$+$14.6} at semantic, and \textbf{$+$10.4} at panoptic level on COCO, with even larger gains on Pascal VOC, while requiring a single model instead of three. Code will be made available upon acceptance.

cs.CV↗

arXiv2026

Efficient Reinforcement Learning by Guiding World Models with Non-Curated Data

Leveraging offline data is a promising way to improve the sample efficiency of online reinforcement learning (RL). This paper expands the pool of usable data for offline-to-online RL by leveraging abundant non-curated data that is reward-free, of mixed quality, and collected across multiple embodiments. Although learning a world model appears promising for utilizing such data, we find that naive fine-tuning fails to accelerate RL training on many tasks. Through careful investigation, we attribute this failure to the distributional shift between offline and online data during fine-tuning. To address this issue and effectively use the offline data, we propose two techniques: \emph{i)} experience rehearsal and \emph{ii)} execution guidance. With these modifications, the non-curated offline data substantially improves RL's sample efficiency. Under limited sample budgets, our method achieves nearly twice the aggregate score of learning-from-scratch baselines across 72 visuomotor tasks spanning 6 embodiments. On challenging tasks such as locomotion and robotic manipulation, it outperforms prior methods that utilize offline data by a decent margin.

cs.LG↗

arXiv2026

Internalizing Temporal Consistency in Video Object-Centric Learning without Explicit Regularization

Video Object-Centric Learning (OCL) aims to represent objects as \textit{slot} vectors and maintain their consistency across frames. Slot-Slot Contrastive (SSC) loss has become the cornerstone for state-of-the-art (SOTA) video OCL methods. While highly effective, SSC relies on one-to-one object correspondence across frames and introduces an extra loss. Following Occam's Razor, we propose a paradigm shift: temporal consistency is better enforced as an implicit model design rather than an explicit loss. To elegantly exclude SSC (\textbf{xSSC}), we introduce two quasi-zero-overhead synergistic mechanisms: (\textit{i}) Chrono-Channel Decomposition (CCD) structurally disentangles slot representations along the channel dimension into \textit{static} and \textit{dynamic} sub-spaces, serving as an empirically unified information bottleneck; (\textit{ii}) Cross-Temporal Reconstruction (CTR) stochastically reconstructs target features of either the current or previous time step by fusing current slots' static channels and target slots' dynamic channels, using a single standard OCL decoder with minor training adaptation. Thereby, the slot sets inherently learn temporal consistency by minimizing the standard reconstruction error alone. Extensive experiments show that integrating xSSC into leading baselines not only improves training efficiency but also establishes new SOTAs on video object discovery and recognition tasks. Furthermore, our PCA and gradient analyses confirm that objects' time-invariant semantics and time-variant kinematics are encoded into the proposed sub-spaces. Our source code, model checkpoints and training logs are provided on https://github.com/Genera1Z/xSSC.

cs.CV↗

arXiv2026

Cycle Consistency in Video Object-Centric Learning

Self-supervised video Object-Centric Learning (OCL) aims to discover distinct objects and associate them across time, whereas self-supervised Multi-Object Tracking (MOT) focuses on associating pre-defined object detections or segmentations. Although well-established in MOT, Cycle Consistency (CC) cannot naively or explicitly apply to the latent slot space of OCL. Unlike the deterministic and ideal object representations in MOT, OCL slots are inherently stochastic and ambiguous due to non-unique scene decompositions. Enforcing explicit cycle consistency (ECC) on slots imposes rigid mean seeking. This severely penalizes the model for exploring alternative but equally valid decompositions, thereby driving towards feature collapse. To resolve this dilemma, we propose \textit{Implicit Cycle Consistency (ICC)}, which shifts the cycle-consistency constraint from the restrictive slot space to the continuous reconstruction manifold, encouraging slots to reach a soft consensus on collectively interpreting the visual scene rather than forcing rigid point-to-point feature alignment. Extensive experiments on complex video OCL benchmarks demonstrate that ICC avoids feature collapse and outperforms ECC baselines. Our source code, model checkpoints and training logs are provided on https://github.com/Genera1Z/ICC.

cs.CV↗

arXiv2026

Smoothing Slot Attention Iterations and Recurrences

Slot Attention (SA) lies at the heart of mainstream Object-Centric Learning (OCL). Image features can be aggregated into object-level representations by SA \textit{iteratively} refining cold-start query slots. For video, such aggregation proceeds by SA \textit{recurrently} shared across frames, with queries cold-started on the first frame while transitioned from the previous frame's slots thereafter. However, cold-start queries lack sample-specific cues thus hindering precise aggregation on image or video's first frame; Non-first frames' queries are already sample-specific thus requiring aggregation transforms different from the first frame. We address these issues with our \textit{SmoothSA}: (1) To smooth SA iterations on image or video's first frame, we \textit{preheat} cold-start queries with rich input-feature information, by a tiny module self-distilled inside OCL; (2) To smooth SA recurrences across video's first and non-first frames, we \textit{differentiate} the homogeneous aggregation transforms by using full and single iterations respectively. Comprehensive experiments on object discovery, recognition and visual reasoning validate our method's effectiveness. Further visual analyses illuminate the underline mechanisms. Our \textit{source code}, \textit{model checkpoints} and \textit{training logs} are provided on https://github.com/Genera1Z/SmoothSA.

cs.CV↗

arXiv2026

Point Tracking Improves World Action Models

Robot policy learning benefits from world-action models that capture environment dynamics, but pixel-level prediction entangles dynamics with nuisance factors such as lighting and texture, making learned representations vulnerable to task-irrelevant visual variation. We propose JOPAT, a JOint Pixel-And-Track World-Action Model that predicts latent visual observations, 2D point tracks with visibility, and actions in a single denoising diffusion transformer. The key insight is that tracks provide an explicit representation of motion that captures long-horizon dynamics and remains robust under occlusion or partial out-of-frame motion, offering greater utility than modeling pixel appearance alone. On LIBERO and real-world LeRobot tasks, JOPAT improves over pixel-based baselines, with the largest gains on long-horizon tasks involving occlusion, object interaction, and off-screen motion.

cs.RO↗

arXiv2026

Cross-View Splatter: Feed-Forward View Synthesis with Georeferenced Images

We present Cross-View Splatter, a feed-forward method that predicts pixel-aligned Gaussian splats for outdoor scenes captured at ground level AND by satellite. Faithful reconstructions require good camera coverage, but ground imagery is time-consuming and hard to capture at scale for large outdoor scenes. Fortunately, satellite imagery can provide a global geometric prior that is easy to access via public APIs. Cross-View Splatter fuses orthorectified satellite views with GPS-tagged ground photos to predict Gaussian splats in a unified 3D coordinate frame. By aligning ground and bird's-eye feature representations, our model improves scene coverage and novel-view synthesis, compared to ground imagery alone. We train on curated georeferenced datasets and paired satellite-terrain data, mined from open mapping services. We evaluate our method on a new benchmark for novel-view synthesis with georeferenced imagery allowing comparison to prior state-of-the-art methods. Our code and data preparation will be available at https://nianticspatial.github.io/cross-view-splatter/.

cs.CV↗

arXiv2026

OP2GS: Object-Aware 3D Gaussian Splatting with Dual-Opacity Primitives

3D Gaussian Splatting (3DGS) provides an explicit and efficient scene representation, but its primitives lack inherent object-level identity, hindering downstream tasks such as open-vocabulary scene understanding. Existing methods typically address this by either distilling high-dimensional feature embeddings into Gaussians or by lifting 2D mask labels into 3D via heuristic refinement. However, feature-based approaches incur heavy storage and decoding overhead, while lifting-based pipelines remain vulnerable to label contamination: Gaussians necessary for appearance reconstruction often receive incorrect object labels during 2D-to-3D projection. We propose OP2GS, an object-aware Gaussian representation that augments each primitive with an explicit instance identity and a dedicated instance opacity $σ^{*}$ for object-mask rendering. The original opacity $σ$ remains responsible for visual reconstruction, while $σ^{*}$ models whether a Gaussian should contribute to a particular object mask. This dual-opacity formulation decouples visual existence from instance occupancy: mislabeled Gaussians can remain available for image rendering while becoming transparent in the object-mask branch. To learn this representation, we introduce a random object loss that optimizes the 1D instance occupancy field using the standard transmittance-based visibility of 3DGS. Semantic descriptors are then attached at the object level through multi-view aggregation, eliminating per-Gaussian feature storage. Compared with feature-training approaches, OP2GS achieves competitive open-vocabulary performance while significantly reducing computational overhead. Compared with training-free pipelines, it leverages physically consistent occupancy learning to resolve visibility ambiguities.

cs.CV↗

arXiv2026

Predicting Video Slot Attention Queries from Random Slot-Feature Pairs

Unsupervised video Object-Centric Learning (OCL) is promising as it enables object-level scene representation and understanding as we humans do. Mainstream video OCL methods adopt a recurrent architecture: An aggregator aggregates current video frame into object features, termed slots, under some queries; A transitioner transits current slots to queries for the next frame. This is an effective architecture but all existing implementations both (\textit{i1}) neglect to incorporate next frame features, the most informative source for query prediction, and (\textit{i2}) fail to learn transition dynamics, the knowledge essential for query prediction. To address these issues, we propose Random Slot-Feature pair for learning Query prediction (RandSF.Q): (\textit{t1}) We design a new transitioner to incorporate both slots and features, which provides more information for query prediction; (\textit{t2}) We train the transitioner to predict queries from slot-feature pairs randomly sampled from available recurrences, which drives it to learn transition dynamics. Experiments on scene representation demonstrate that our method surpass existing video OCL methods significantly, e.g., up to 10 points on object discovery, setting new state-of-the-art. Such superiority also benefits downstream tasks like scene understanding. Source Code, Model Checkpoints, Training Logs: https://github.com/Genera1Z/RandSF.Q

cs.CV↗

arXiv2026

Latent-Compressed Variational Autoencoder for Video Diffusion Models

Video variational autoencoders (VAEs) used in latent diffusion models typically require a sufficiently large number of latent channels to ensure high-quality video reconstruction. However, recent studies have revealed that an excessive number of latent channels can impede the convergence of latent diffusion models and deteriorate their generative performance, even when reconstruction quality remains high. We propose a latent compression method that removes high-frequency components in video latent representations rather than directly reducing the number of channels, which often compromises reconstruction fidelity. Experimental results demonstrate that the proposed method achieves superior video reconstruction quality compared to strong baselines while maintaining the same overall compression ratio.

cs.CV↗

arXiv2026

Scene-Agnostic Object-Centric Representation Learning for 3D Gaussian Splatting

Recent works on 3D scene understanding leverage 2D masks from visual foundation models (VFMs) to supervise radiance fields, enabling instance-level 3D segmentation. However, the supervision signals from foundation models are not fundamentally object-centric and often require additional mask pre/post-processing or specialized training and loss design to resolve mask identity conflicts across views. The learned identity of the 3D scene is scene-dependent, limiting generalizability across scenes. Therefore, we propose a dataset-level, object-centric supervision scheme to learn object representations in 3D Gaussian Splatting (3DGS). Building on a pre-trained slot attention-based Global Object Centric Learning (GOCL) module, we learn a scene-agnostic object codebook that provides consistent, identity-anchored representations across views and scenes. By coupling the codebook with the module's unsupervised object masks, we can directly supervise the identity features of 3D Gaussians without additional mask pre-/post-processing or explicit multi-view alignment. The learned scene-agnostic codebook enables object supervision and identification without per-scene fine-tuning or retraining. Our method thus introduces unsupervised object-centric learning (OCL) into 3DGS, yielding more structured representations and better generalization for downstream tasks such as robotic interaction, scene understanding, and cross-scene generalization.

cs.CV↗

arXiv2026

PAWS: Perception of Articulation in the Wild at Scale from Egocentric Videos

Articulation perception aims to recover the motion and structure of articulated objects (e.g., drawers and cupboards), and is fundamental to 3D scene understanding in robotics, simulation, and animation. Existing learning-based methods rely heavily on supervised training with high-quality 3D data and manual annotations, limiting scalability and diversity. To address this limitation, we propose PAWS, a method that directly extracts object articulations from hand-object interactions in large-scale in-the-wild egocentric videos. We evaluate our method on the public data sets, including HD-EPIC and Arti4D data sets, achieving significant improvements over baselines. We further demonstrate that the extracted articulations benefit downstream tasks, including fine-tuning 3D articulation prediction models and enabling robot manipulation. See the project website at https://aaltoml.github.io/PAWS/.

cs.CV↗

arXiv2026

3D Gaussian Splatting with Fisheye Images: Field of View Analysis and Depth-Based Initialization

We present the first evaluation of 3D Gaussian Splatting methods on real fisheye imagery with fields of view above 180\textdegree{}. Our study evaluates Fisheye-GS \cite{liao2024fisheyegslightweightextensiblegaussian} and 3DGUT \cite{wu20253dgut} on indoor and outdoor scenes captured with 200\textdegree{} fisheye cameras, with the aim of assessing the practicality of wide-angle reconstruction under severe distortion. By comparing reconstructions at 200\textdegree{}, 160\textdegree{}, and 120\textdegree{} field-of-view, we show that both methods achieve their best results at 160\textdegree{}, which balances scene coverage with image quality, while distortion at 200\textdegree{} degrades performance. To address the common failure of Structure-from-Motion (SfM) initialization at such wide angles, we introduce a depth-based alternative using UniK3D (Universal Camera Monocular 3D Estimation) \cite{piccinelli2025unik3d}. This represents the first application of UniK3D to fisheye imagery beyond 200\textdegree{}, despite the model not being trained on such data. With the number of predicted points controlled to match SfM for fairness, UniK3D produces geometrically accurate reconstructions that rival or surpass SfM, even in challenging scenes with fog, glare, or open sky. These results demonstrate the feasibility of fisheye-based 3D Gaussian Splatting and provides a benchmark for future research on wide-angle reconstruction from sparse and distorted inputs.

cs.CV↗